PaperTrail / outputs /requests.json
AdarshRL's picture
Publish PaperTrail from pinned public source
f7f8a1e verified
Raw History Blame Contribute Delete
83.6 kB
{"candidate_sha256":"0c8d2b3187658a15e1224a35345cbd838303b688afa1afc60434f925467f4a3c","corpus_revision":"8b99f07e2773aaa7996ce5e18be617a714ef5c78ed77de6ac00737554dcdd3a7","input_sha256":"9458bfe76074a8fa8d1685af02bcc73537aa6d338ad20591dfaff1946bc88bf4","mode":"dense","prompt_version":"quoted-answer-v2-prefill","rows":[{"paper_id":"1601.00901","passages":[{"kind":"paragraph","paper_id":"1601.00901","passage_id":"1601.00901:paragraph:0:1","position":1,"section_index":0,"section_name":"Introduction","source_file":null,"text":"In this paper, we propose a novel approach to joint learning of ontology and semantic parsing, which is designed for homogeneous collections of text, where each fact is usually stated only once, therefore we cannot rely on data redundancy. Our approach is text-driven, semi-automatic and based on grammar induction. It is presented in Figure 1 .The input is a seed ontology together with text annotated with concepts from the seed ontology. The result of the process is an ontology with extended instances, classes, taxonomic and non-taxonomic relations, and a semantic parser, which transform basic units of text, i.e sentences, into semantic trees. Compared to trees that structure sentences based on syntactic information, nodes of semantic trees contain semantic classes, like location, profession, color, etc. Our approach does not rely on any syntactic analysis of text, like part-of-speech tagging or dependency parsing. The grammar induction method works on the premise of curriculum learning BIBREF7 , where the parser first learns to parse simple sentences, then proceeds to learn more complex ones. The induction method is iterative, semi-automatic and based on frequent patterns. A context-free grammar (CFG) is induced from the text, which is represented by several layers of semantic annotations. The motivation to use CFG is that it is very suitable for the proposed alternating usage of top-down and bottom-up parsing, where new rules are induced from previously unparsable parts. Furthermore, it has been shown by BIBREF8 that CFGs are expressive enough to model almost every language phenomena. The induction is based on a greedy iterative procedure that involves minor human involvement, which is needed for seed rule definition and rule categorization. Our experiments show that although the grammar is ambiguous, it is scalable enough to parse a large dataset of sentences."},{"kind":"paragraph","paper_id":"1601.00901","passage_id":"1601.00901:paragraph:12:2","position":2,"section_index":12,"section_name":"Grammar Induction Experiments","source_file":null,"text":"The grammar was also tested by parsing a sample of 100.000 test sentences. A few statistic are presented in Table 4 . More than a quarter of sentences were fully parsed, meaning that they do not have any null leaf nodes. Coverage represents the fraction of words in a sentence that were parsed (words that are not in null-nodes). The number of operations shows how many times was the Parse function called during the parsing of a sentences. It is highly correlated with the time spend for parsing a sentence, which is on average 0.16ms. This measurement was done on a single CPU core. Consequently, it is feasible to parse a collection of a million sentences, like our dataset. The same statistics were also calculated on the training set, the numbers are very similar to the test set. The fully parsed % and coverage are even slightly lower than on the test set. Some of the statistics were calculated after each iteration, but only when a non neutral rule was created. The graphs in Figure 5 show how have the statistics changed over the course of the grammar induction. Graph 5 shows that coverage and the fraction of fully parsed sentences are correlated and they grow very rapidly at the beginning, then the growth starts to slow down, which indicates that there is a long tail of unparsed nodes/sentences. In the following section, we present a concept learning method, which deals with the long tail. Furthermore, the number of operations per sentence also slows down (see Graph 5 ) with the number of rules, which gives a positive sign of retaining computational feasibility with the growth of the grammar. Graph 5 somewhat elaborates the dynamics of the grammar induction. In the earlier phase of induction many rules that define the upper structure of the tree are induced. These rules can rapidly increase the depth and number of null nodes, like rule 1 and rule 2 . They also explain the spikes on Graph 5 . Their addition to the grammar causes some rules to emerge on the top of the list with a significantly higher frequency. After these rules are induced the frequency gets back to the previous values and slowly decreases over the long run."},{"kind":"caption","paper_id":"1601.00901","passage_id":"1601.00901:caption:0","position":0,"section_index":null,"section_name":"Figures and tables","source_file":"3-Figure1-1.png","text":"Figure 1. The proposed approach to ontology and grammar induction gets a collection of text and the seed ontology as input and outputs a new ontology. The collection of text is first annotated at different levels including annotations with the concepts from existing ontology. The annotated text is then used for grammar induction, where the text is represented as semantic trees. These are used together with the grammar to induce a new ontology."},{"kind":"caption","paper_id":"1601.00901","passage_id":"1601.00901:caption:1","position":1,"section_index":null,"section_name":"Figures and tables","source_file":"4-Figure2-1.png","text":"Figure 2. Grammar induction"},{"kind":"paragraph","paper_id":"1601.00901","passage_id":"1601.00901:paragraph:1:1","position":1,"section_index":1,"section_name":"Grammar induction","source_file":null,"text":"The input to the process, which is illustrated in Figure 2 , is a set of predefined seed grammar rules (see Section \"Seed rules\" ) and a sample of sentences in a layered representation (see Section \"Experiments\" ) from the dataset. The output of the process is a larger set of rules forming the induced grammar. One rule is added to the grammar on each iteration. At the beginning of each iteration all the sentences are parsed with a top-down parser. The output of parsing a single sentence is a semantic tree – a set of semantic nodes connected into a tree. Here we distinguish two possible outcomes of the parsing: 1) the sentence was completely parsed, which is the final goal and 2) there is at least one part of the sentence that cannot be parsed. From the perspective of a parser the second scenario happens when there is a node that cannot be parsed by any of the rules. We name these nodes – null nodes – and they serve as the input for the next step, the rule induction. In this step several rules are constructed by generalization of null nodes. The generalization (see Section \"Rule induction\" ) is based on utilization of semantic annotations and bottom-up composition of the existing rules. Out of the induced rules, a rule with the highest frequency (the one that was generalized from the highest number of null nodes) is added to the grammar. To improve quality of the grammar, the rules are marked by so called property, which instructs the parser how to use the rule (eg., us it in parsing but not in induction). The property vitally affects result of the parsing in the following iterations potentially causing a huge semantic drift for the rest of process. Consequently, a human user needs to mark the property of each rule. The iterative process runs until a predefined stopping criteria is met. The criteria is either connected to the quality of the grammar or time limitation."}],"question":"How did they induce the CFG?","question_id":"74b0d3ee0cc9b0a3d9b264aba9901ff97048a897"},{"paper_id":"1601.00901","passages":[{"kind":"paragraph","paper_id":"1601.00901","passage_id":"1601.00901:paragraph:12:2","position":2,"section_index":12,"section_name":"Grammar Induction Experiments","source_file":null,"text":"The grammar was also tested by parsing a sample of 100.000 test sentences. A few statistic are presented in Table 4 . More than a quarter of sentences were fully parsed, meaning that they do not have any null leaf nodes. Coverage represents the fraction of words in a sentence that were parsed (words that are not in null-nodes). The number of operations shows how many times was the Parse function called during the parsing of a sentences. It is highly correlated with the time spend for parsing a sentence, which is on average 0.16ms. This measurement was done on a single CPU core. Consequently, it is feasible to parse a collection of a million sentences, like our dataset. The same statistics were also calculated on the training set, the numbers are very similar to the test set. The fully parsed % and coverage are even slightly lower than on the test set. Some of the statistics were calculated after each iteration, but only when a non neutral rule was created. The graphs in Figure 5 show how have the statistics changed over the course of the grammar induction. Graph 5 shows that coverage and the fraction of fully parsed sentences are correlated and they grow very rapidly at the beginning, then the growth starts to slow down, which indicates that there is a long tail of unparsed nodes/sentences. In the following section, we present a concept learning method, which deals with the long tail. Furthermore, the number of operations per sentence also slows down (see Graph 5 ) with the number of rules, which gives a positive sign of retaining computational feasibility with the growth of the grammar. Graph 5 somewhat elaborates the dynamics of the grammar induction. In the earlier phase of induction many rules that define the upper structure of the tree are induced. These rules can rapidly increase the depth and number of null nodes, like rule 1 and rule 2 . They also explain the spikes on Graph 5 . Their addition to the grammar causes some rules to emerge on the top of the list with a significantly higher frequency. After these rules are induced the frequency gets back to the previous values and slowly decreases over the long run."},{"kind":"paragraph","paper_id":"1601.00901","passage_id":"1601.00901:paragraph:12:0","position":0,"section_index":12,"section_name":"Grammar Induction Experiments","source_file":null,"text":"The grammar was induced on 10.000 random sentences taken from the dataset described in Section \"Datasets\" . First, a list of 45 seed nodes was constructed. There were 22 domain independent linguistic rules, 17 category rules and 6 top-level rules. The property assignment was done by the authors. In every iteration, the best rule is shown together with the number of nodes it was induced from, and ten of those nodes together with the sentences they appear in. The goal was set to stop the iterative process after two hours. We believe this is the right amount of time to still expect quality feedback from a human user."},{"kind":"paragraph","paper_id":"1601.00901","passage_id":"1601.00901:paragraph:11:3","position":3,"section_index":11,"section_name":"Datasets","source_file":null,"text":"There are almost 1.1 million sentences in the collection. The average length of a sentence is 18.3 words, while the median length is 13.8 words. There are 2.3 links per sentence."},{"kind":"paragraph","paper_id":"1601.00901","passage_id":"1601.00901:paragraph:19:0","position":0,"section_index":19,"section_name":"Discussion","source_file":null,"text":"We have presented an approach for joint ontology learning and semantic parsing. The approach was evaluated by building an ontology representing biographies of people. The first sentences of person Wikipedia pages and the combination of DBpedia and Freebase were used as a dataset. This dataset was suitable for our approach, because the text is equipped with human tagged annotations, which are already linked to the ontology. In other cases a named entity disambiguation would be needed to obtain the annotations. The next trait of the dataset, that is suitable for our approach, is the homogeneous style of writing. Otherwise, if the style was more heterogeneous, the users would have to participate in more iterations to achieve the same level of coverage. The participation of the users may be seen a cost, but on the other hand it allows them to learn about the dataset without reading it all. The users does not learn so much about specific facts as they learn about the second order information, like what types of relations are expressed and their distribution."},{"kind":"paragraph","paper_id":"1601.00901","passage_id":"1601.00901:paragraph:11:0","position":0,"section_index":11,"section_name":"Datasets","source_file":null,"text":"The datasets for experiments were constructed from English Wikipedia and knowledge bases DBpedia BIBREF9 and Freebase BIBREF6 . DBpedia provides structured information about Wikipedia articles that was scraped out of their infoboxes. First sentences of Wikipedia pages describing people were taken as the textual dataset, while DBpedia relations expressing facts about the same people were taken as the dataset for supervised relation learning. Note that each DBpedia instance has a Wikipedia page. A set of person instances was identified by querying DBpedia for instances that have a person class. For the textual dataset, Wikipedia pages representing these entities were parsed by the in-house Wikipedia markup parser to convert the markup into plain text. Furthermore, the links to other Wikipedia pages were retained. Here is an example of a sentence in plain text:"}],"question":"How big is their dataset?","question_id":"9eb5b336b3dcb7ab63f673ba9ab1818573cce6c3"},{"paper_id":"1601.01705","passages":[{"kind":"abstract","paper_id":"1601.01705","passage_id":"1601.01705:abstract:0","position":0,"section_index":null,"section_name":"Abstract","source_file":null,"text":"We describe a question answering model that applies to both images and structured knowledge bases. The model uses natural language strings to automatically assemble neural networks from a collection of composable modules. Parameters for these modules are learned jointly with network-assembly parameters via reinforcement learning, with only (world, question, answer) triples as supervision. Our approach, which we term a dynamic neural model network, achieves state-of-the-art results on benchmark datasets in both visual and structured domains."},{"kind":"paragraph","paper_id":"1601.01705","passage_id":"1601.01705:paragraph:7:0","position":0,"section_index":7,"section_name":"Questions about images","source_file":null,"text":"Our first task is the recently-introduced Visual Question Answering challenge (VQA) BIBREF22 . The VQA dataset consists of more than 200,000 images paired with human-annotated questions and answers, as in fig:vqa:qualitative-results."},{"kind":"caption","paper_id":"1601.01705","passage_id":"1601.01705:caption:5","position":5,"section_index":null,"section_name":"Figures and tables","source_file":"8-Table2-1.png","text":"Table 2: Results on the GeoQA dataset, and the GeoQA dataset with quantification. Our approach outperforms both a purely logical model (LSP-F) and a model with learned perceptual predicates (LSP-W) on the original dataset, and a fixedstructure NMN under both evaluation conditions."},{"kind":"paragraph","paper_id":"1601.01705","passage_id":"1601.01705:paragraph:6:0","position":0,"section_index":6,"section_name":"Experiments","source_file":null,"text":"The framework described in this paper is general, and we are interested in how well it performs on datasets of varying domain, size and linguistic complexity. To that end, we evaluate our model on tasks at opposite extremes of both these criteria: a large visual question answering dataset, and a small collection of more structured geography questions."},{"kind":"paragraph","paper_id":"1601.01705","passage_id":"1601.01705:paragraph:7:1","position":1,"section_index":7,"section_name":"Questions about images","source_file":null,"text":"We use the VQA 1.0 release, employing the development set for model selection and hyperparameter tuning, and reporting final results from the evaluation server on the test-standard set. For the experiments described in this section, the input feature representations $w_i$ are computed by the the fifth convolutional layer of a 16-layer VGGNet after pooling BIBREF12 . Input images are scaled to 448 $\\times $ 448 before computing their representations. We found that performance on this task was best if the candidate layouts were relatively simple: only describe, and and find modules are used, and layouts contain at most two conjuncts."}],"question":"What benchmark datasets they use?","question_id":"5712a0b1e33484ebc6d71c70ae222109c08dede2"},{"paper_id":"1601.02166","passages":[{"kind":"paragraph","paper_id":"1601.02166","passage_id":"1601.02166:paragraph:0:1","position":1,"section_index":0,"section_name":"Cross-lingual transfer learning of sequence models","source_file":null,"text":"What can we do for all the languages for which no training data is available? Unsupervised POS induction algorithms have methodological problems (in-sample evaluation, community-wide hyper-parameter tuning, etc.), and performance is prohibitive of downstream applications. Some work on unsupervised POS tagging has assumed other resources such as tag dictionaries BIBREF0 , but such resources are also only available for a limited number of languages. In our experiments, we assume that no training data or tag dictionaries are available. Our only assumption is a bit of text translated into multiple languages, specifically, fragments of the Bible. We will use Bible data for annotation projection, as well as for learning cross-lingual word embeddings (§3)."},{"kind":"paragraph","paper_id":"1601.02166","passage_id":"1601.02166:paragraph:0:3","position":3,"section_index":0,"section_name":"Cross-lingual transfer learning of sequence models","source_file":null,"text":"Annotation projection refers to transferring annotation from one or more source languages to the target language (for which no labeled data is otherwise available), typically through word alignments. In our experiments below, we use an unsupervised word alignment algorithm to align $15\\times 12$ language pairs. For 15 languages, we have predicted POS tags for each word in our multi-parallel corpus. For each word in one of our 12 target language training datasets, we thus have up to 15 votes for each word token, possibly weighted by the confidence of the word alignment algorithm. In this paper, we simply use the majority votes. This is the set-up assumed throughout in this paper (see §3 for more details):"},{"kind":"paragraph","paper_id":"1601.02166","passage_id":"1601.02166:paragraph:1:1","position":1,"section_index":1,"section_name":"Empirical Gaussian priors","source_file":null,"text":"When we estimate Gaussian priors from source language models, we will learn which features are invariant across languages, and which are not. We thereby introduce an ellipsoid regularizer whose centre is the average source model. In our experiments, we consider both the case where variance is assumed to be constant – which we call L2-regularization with priors (L2-Prior) — and the case where both variances and means are learned – which we call empirical Gaussian priors (EmpGauss). L2-Prior is the L2-CRF objective with $\\sigma ^2_j=C$ with $C$ a regularization parameter, and $\\mu _j=\\hat{\\mu _j}$ the average value of the corresponding parameter in the observed source models. EmpGauss replaces the above objective with $LL(\\lambda )+\\sum _j\\log \\frac{1}{\\sigma \\sqrt{2\\pi }}e^{-\\frac{(\\lambda _j-\\mu _j)^2}{2\\sigma ^2}}$ , which, assuming model parameters are mutually independent, is the same as jointly optimising model probability and likelihood of the data. Note that minimizing the squared weights is equivalent to maximizing the log probability of the weights under a zero-mean Gaussian prior, and in the same way, this is equivalent to minimising the above objective with empirically estimated parameters $\\hat{\\mu _j}$ and $\\sigma {\\mu _j}$ . In other words, empirical Gaussian priors are bounding ellipsoids on the hypothesis space with learned widths and centres. Also, note that in single-source cross-lingual transfer learning, observed variance is zero, and we therefore replace this with a regularization parameter $C$ shared with the baseline. In the single-source set-up, L2-Prior is thus equivalent to EmpGauss. We use L-BFGS to maximize our baseline L2-regularized objectives, as well as our empirical Gaussian prior objectives."},{"kind":"paragraph","paper_id":"1601.02166","passage_id":"1601.02166:paragraph:0:0","position":0,"section_index":0,"section_name":"Cross-lingual transfer learning of sequence models","source_file":null,"text":"The people of the world speak about 6,900 different languages. Open-source off-the-shelf natural language processing (NLP) toolboxes like OpenNLP and CoreNLP cover only 6–7 languages, and we have sufficient labeled training data for inducing models for about 20–30 languages. In other words, supervised sequence learning algorithms are not sufficient to induce POS models for but a small minority of the world's languages."},{"kind":"abstract","paper_id":"1601.02166","passage_id":"1601.02166:abstract:0","position":0,"section_index":null,"section_name":"Abstract","source_file":null,"text":"Sequence model learning algorithms typically maximize log-likelihood minus the norm of the model (or minimize Hamming loss + norm). In cross-lingual part-of-speech (POS) tagging, our target language training data consists of sequences of sentences with word-by-word labels projected from translations in $k$ languages for which we have labeled data, via word alignments. Our training data is therefore very noisy, and if Rademacher complexity is high, learning algorithms are prone to overfit. Norm-based regularization assumes a constant width and zero mean prior. We instead propose to use the $k$ source language models to estimate the parameters of a Gaussian prior for learning new POS taggers. This leads to significantly better performance in multi-source transfer set-ups. We also present a drop-out version that injects (empirical) Gaussian noise during online learning. Finally, we note that using empirical Gaussian priors leads to much lower Rademacher complexity, and is superior to optimally weighted model interpolation."}],"question":"What languages did they experiment with?","question_id":"e67d2266476abd157fc8c396b3dfb70cb343471e"},{"paper_id":"1601.02543","passages":[{"kind":"paragraph","paper_id":"1601.02543","passage_id":"1601.02543:paragraph:3:0","position":0,"section_index":3,"section_name":"Conclusion","source_file":null,"text":"In this paper we proposed a methodology to identify words that could lead to confusion at any given node of a speech recognition based system. We used edit distance as the metric to identifying the possible confusion between the active words. We showed that this metric can be used effectively to enhance the performance of a speech solution without actually putting it to people test. There is a significant saving in terms of being able to identify recognition bottlenecks in a menu based speech solution through this analysis because it does not require actual people testing the system. This methodology was adopted to restructuring the set of active words at each node for better speech recognition in an actual menu based speech recognition system that caters to masses."},{"kind":"paragraph","paper_id":"1601.02543","passage_id":"1601.02543:paragraph:1:2","position":2,"section_index":1,"section_name":"Evaluation without Testing","source_file":null,"text":"We hypothesize that we can identify the performance of a menu based speech system by identifying the possible confusion among all the words that are active at a given node. If active words at a given node are phonetically similar it becomes difficult for the speech recognition system to distinguish them which in turn leads to recognition errors. We used Levenshtein distance BIBREF4 , BIBREF5 a well known measure to analyze and identify the confusion among the active words at a given node. This analysis gives a list of all set of words that have a high degree of confusability among them; this understanding can be then used to (a) restructure the set of active words at that node and/or (b) train the words that can be confused by using a larger corpus of speech data. This allows the speech recognition engine to be equipped to be able to distinguish the confusing words better. Actual use of this analysis was carried out for a speech solution developed for Indian Railway Inquiry System to identify bottlenecks in the system before its actual launch."},{"kind":"abstract","paper_id":"1601.02543","passage_id":"1601.02543:abstract:0","position":0,"section_index":null,"section_name":"Abstract","source_file":null,"text":"Speech based solutions have taken center stage with growth in the services industry where there is a need to cater to a very large number of people from all strata of the society. While natural language speech interfaces are the talk in the research community, yet in practice, menu based speech solutions thrive. Typically in a menu based speech solution the user is required to respond by speaking from a closed set of words when prompted by the system. A sequence of human speech response to the IVR prompts results in the completion of a transaction. A transaction is deemed successful if the speech solution can correctly recognize all the spoken utterances of the user whenever prompted by the system. The usual mechanism to evaluate the performance of a speech solution is to do an extensive test of the system by putting it to actual people use and then evaluating the performance by analyzing the logs for successful transactions. This kind of evaluation could lead to dissatisfied test users especially if the performance of the system were to result in a poor transaction completion rate. To negate this the Wizard of Oz approach is adopted during evaluation of a speech system. Overall this kind of evaluations is an expensive proposition both in terms of time and cost. In this paper, we propose a method to evaluate the performance of a speech solution without actually putting it to people use. We first describe the methodology and then show experimentally that this can be used to identify the performance bottlenecks of the speech solution even before the system is actually used thus saving evaluation time and expenses."},{"kind":"paragraph","paper_id":"1601.02543","passage_id":"1601.02543:paragraph:2:3","position":3,"section_index":2,"section_name":"Case Study","source_file":null,"text":"Table TABREF6 shows the list of active word at the node 1 when the speech application was initially designed and Table TABREF7 shows the edit distance between all the active words at the node service given in Fig. FIGREF4 . The distance between words Sahi and Galat was found to be INLINEFORM0 which was set at the threshold, namely INLINEFORM1 . This threshold value was used to identify confusing active words. Clearly, as seen in the Table the distance between word pairs fare, pnr and pnr, prasthan is INLINEFORM2 and INLINEFORM3 respectively, which is very close to the threshold value of INLINEFORM4 . This can cause a high possibility that /fare/ may get recognized as pnr and vice-versa."},{"kind":"paragraph","paper_id":"1601.02543","passage_id":"1601.02543:paragraph:0:0","position":0,"section_index":0,"section_name":"Introduction","source_file":null,"text":"There are several commercial menu based ASR systems available around the world for a significant number of languages and interestingly speech solution based on these ASR are being used with good success in the Western part of the globe BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 . Typically, a menu based ASR system restricts user to speak from a pre-defined closed set of words for enabling a transaction. Before commercial deployment of a speech solution it is imperative to have a quantitative measure of the performance of the speech solution which is primarily based on the speech recognition accuracy of the speech engine used. Generally, the recognition performance of any speech recognition based solution is quantitatively evaluated by putting it to actual use by the people who are the intended users and then analyzing the logs to identify successful and unsuccessful transactions. This evaluation is then used to identifying any further improvement in the speech recognition based solution to better the overall transaction completion rates. This process of evaluation is both time consuming and expensive. For evaluation one needs to identify a set of users and also identify the set of actual usage situations and perform the test. It is also important that the set of users are able to use the system with ease meaning that even in the test conditions the performance of the system, should be good, while this can not usually be guaranteed this aspect of keeping the user experience good makes it necessary to employ a wizard of Oz (WoZ) approach. Typically this requires a human agent in the loop during actual speech transaction where the human agent corrects any mis-recognition by actually listening to the conversation between the human user and the machine without the user knowing that there is a human agent in the loop. The use of WoZ is another expense in the testing a speech solution. All this makes testing a speech solution an expensive and time consuming procedure."}],"question":"what bottlenecks were identified?","question_id":"8d793bda51a53a4605c1c33e7fd20ba35581a518"},{"paper_id":"1601.04012","passages":[{"kind":"paragraph","paper_id":"1601.04012","passage_id":"1601.04012:paragraph:20:27","position":27,"section_index":20,"section_name":"Determining Event Coreference","source_file":null,"text":"For the experiments, Cybulska and Vossen use the ECB+ dataset BIBREF191 . The ECB+ corpus contains a new corpus component, consisting of 502 texts, describing different instances of event types. They provide results in terms of several metrics: recall, precision and F-score, MUC BIBREF192 , B3 BIBREF184 , mention-based CEAF BIBREF185 , BLANC BIBREF193 , and CoNLL F1 BIBREF194 , and find that the introduction of the granularity concept into similarity computation improves results for every metric."},{"kind":"paragraph","paper_id":"1601.04012","passage_id":"1601.04012:paragraph:19:15","position":15,"section_index":19,"section_name":"Extracting Events","source_file":null,"text":"The TempEval-3 dataset was mostly automatically generated, using a temporal merging system. The half-million token text corpus from English Gigaword2 was automatically annotated using TIPSem, TIPSem-B BIBREF140 and TRIOS BIBREF152 . These systems were re-trained on the TimeBank and AQUAINT corpus, using the TimeML temporal relation set. The outputs of these three state-of-the-art system were merged using a merging algorithm BIBREF151 . The dataset used comprised about 500K tokens of “silver\" standard data and about 100K tokens of “gold\" standard data for training, compared to the corpus of roughly 50K tokens corpus used in TempEval 1 and 2."},{"kind":"caption","paper_id":"1601.04012","passage_id":"1601.04012:caption:11","position":11,"section_index":null,"section_name":"Figures and tables","source_file":"44-TableXI-1.png","text":"Table XI. Evaluation results (recall / precision / f-score for Task 1 in Whole data set (W), Abstracts only (A) and Full papers only (F)"},{"kind":"paragraph","paper_id":"1601.04012","passage_id":"1601.04012:paragraph:16:0","position":0,"section_index":16,"section_name":"Extracting Events from Textual Documents","source_file":null,"text":"Different models of events have been used in computational linguistics work geared toward information extraction."},{"kind":"paragraph","paper_id":"1601.04012","passage_id":"1601.04012:paragraph:19:1","position":1,"section_index":19,"section_name":"Extracting Events","source_file":null,"text":"We describe a few of the approaches that have been used for extracting TimeML type events. Quite a few papers that attempt to do so have been published BIBREF121 , BIBREF138 , BIBREF139 , BIBREF140 , BIBREF141 , and we pick just a few representative papers."}],"question":"Which datasets are used in this work?","question_id":"eac042734f76e787cb98ba3d0c13a916a49bdfb3"},{"paper_id":"1601.06068","passages":[{"kind":"abstract","paper_id":"1601.06068","passage_id":"1601.06068:abstract:0","position":0,"section_index":null,"section_name":"Abstract","source_file":null,"text":"One of the limitations of semantic parsing approaches to open-domain question answering is the lexicosyntactic gap between natural language questions and knowledge base entries -- there are many ways to ask a question, all with the same answer. In this paper we propose to bridge this gap by generating paraphrases of the input question with the goal that at least one of them will be correctly mapped to a knowledge-base query. We introduce a novel grammar model for paraphrase generation that does not require any sentence-aligned paraphrase corpus. Our key idea is to leverage the flexibility and scalability of latent-variable probabilistic context-free grammars to sample paraphrases. We do an extrinsic evaluation of our paraphrases by plugging them into a semantic parser for Freebase. Our evaluation experiments on the WebQuestions benchmark dataset show that the performance of the semantic parser significantly improves over strong baselines."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:11:1","position":1,"section_index":11,"section_name":"Baselines","source_file":null,"text":"We compare our paraphrasing models with monolingual machine translation based model for paraphrase generation BIBREF24 , BIBREF36 . In particular, we use Moses BIBREF37 to train a monolingual phrase-based MT system on the Paralex corpus. Finally, we use Moses decoder to generate 10-best distinct paraphrases for the test questions."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:0:2","position":2,"section_index":0,"section_name":"Introduction","source_file":null,"text":"The main contributions of this paper are two fold. First, we present an algorithm (§ \"Paraphrase Generation Using Grammars\" ) to generate paraphrases using latent-variable PCFGs. We use the spectral method of narayan-15 to estimate L-PCFGs on a large scale question treebank. Our grammar model leads to a robust and an efficient system for paraphrase generation in open-domain question answering. While CFGs have been explored for paraphrasing using bilingual parallel corpus BIBREF14 , ours is the first implementation of CFG that uses only monolingual data. Second, we show that generated paraphrases can be used to improve semantic parsing of questions into Freebase logical forms (§ \"Semantic Parsing using Paraphrasing\" ). We build on a strong baseline of reddylargescale2014 and show that our grammar model competes with MT baseline even without using any parallel paraphrase resources."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:0:1","position":1,"section_index":0,"section_name":"Introduction","source_file":null,"text":"We address the above problems by using paraphrases of the original question. Paraphrasing has shown to be promising for semantic parsing BIBREF9 , BIBREF10 , BIBREF11 . We propose a novel framework for paraphrasing using latent-variable PCFGs (L-PCFGs). Earlier approaches to paraphrasing used phrase-based machine translation for text-based QA BIBREF12 , BIBREF13 , or hand annotated grammars for KB-based QA BIBREF10 . We find that phrase-based statistical machine translation (MT) approaches mainly produce lexical paraphrases without much syntactic diversity, whereas our grammar-based approach is capable of producing both lexically and syntactically diverse paraphrases. Unlike MT based approaches, our system does not require aligned parallel paraphrase corpora. In addition we do not require hand annotated grammars for paraphrase generation but instead learn the grammar directly from a large scale question corpus."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:1:0","position":0,"section_index":1,"section_name":"Paraphrase Generation Using Grammars","source_file":null,"text":"Our paraphrase generation algorithm is based on a model in the form of an L-PCFG. L-PCFGs are PCFGs where the nonterminals are refined with latent states that provide some contextual information about each node in a given derivation. L-PCFGs have been used in various ways, most commonly for syntactic parsing BIBREF15 , BIBREF16 , BIBREF17 , BIBREF18 , BIBREF19 , BIBREF20 ."}],"question":"Do they evaluate the quality of the paraphrasing model?","question_id":"117aa7811ed60e84d40cd8f9cb3ca78781935a98"},{"paper_id":"1601.06068","passages":[{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:9:0","position":0,"section_index":9,"section_name":"Experimental Setup","source_file":null,"text":"Below, we give details on the evaluation dataset and baselines used for comparison. We also describe the model features and provide implementation details."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:13:0","position":0,"section_index":13,"section_name":"Results and Discussion","source_file":null,"text":"In this section, we present results from five different systems for our question-answering experiments: original, mt, naive, ppdb and bilayered. First two are baseline systems. Other three systems use paraphrases generated from an L-PCFG grammar. naive uses a word lattice with a single start-to-end path representing the input question itself, ppdb uses a word lattice constructed using the PPDB rules, and bilayered uses bi-layered L-PCFG to build word lattices. Note that naive does not require any parallel resource to train, ppdb requires an external paraphrase database, and bilayered, like mt, needs a parallel corpus with paraphrase pairs. We tune our classifier features and GraphParser features on the development data. We use the best setting from tuning for evaluation on the test data."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:11:0","position":0,"section_index":11,"section_name":"Baselines","source_file":null,"text":"We use GraphParser without paraphrases as our baseline. This gives an idea about the impact of using paraphrases."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:8:2","position":2,"section_index":8,"section_name":"Learning","source_file":null,"text":"where $\\Phi (p, u, g, q, \\mathcal {K}) \\in \\mathbb {R}^n$ denotes the features for the tuple of paraphrase, ungrounded and grounded graphs. The feature function has access to the paraphrase, ungrounded and grounded graphs, the original question, as well as to the content of the knowledge base and the denotation $|g|_\\mathcal {K}$ (the denotation of a grounded graph is defined as the set of entities or attributes reachable at its target node). See sec:details for the features employed. The model parameters are estimated with the averaged structured perceptron BIBREF35 . Given a training question-answer pair $(q,\\mathcal {A})$ , the update is: $\n\\theta ^{t+1} \\leftarrow \\theta ^{t} + \\Phi (p^+, u^+, g^+, q,\n\\mathcal {K}) - \\Phi (\\hat{p}, \\hat{u}, \\hat{g}, q, \\mathcal {K})\\,,\n$ "},{"kind":"caption","paper_id":"1601.06068","passage_id":"1601.06068:caption:2","position":2,"section_index":null,"section_name":"Figures and tables","source_file":"7-Figure3-1.png","text":"Figure 3: Ungrounded graphs for an input question and its paraphrases along with its correct grounded graph. The green squares indicate NL or Freebase entities, the yellow rectangles indicate unary NL predicates or Freebase types, the circles indicate NL or Freebase events, the edge labels indicate binary NL predicates or Freebase relations, and the red diamonds attach to the entity of interest (the answer to the question)."}],"question":"What are the baselines?","question_id":"423bb905e404e88a168e7e807950e24ca166306c"},{"paper_id":"1601.06068","passages":[{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:1:0","position":0,"section_index":1,"section_name":"Paraphrase Generation Using Grammars","source_file":null,"text":"Our paraphrase generation algorithm is based on a model in the form of an L-PCFG. L-PCFGs are PCFGs where the nonterminals are refined with latent states that provide some contextual information about each node in a given derivation. L-PCFGs have been used in various ways, most commonly for syntactic parsing BIBREF15 , BIBREF16 , BIBREF17 , BIBREF18 , BIBREF19 , BIBREF20 ."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:0:1","position":1,"section_index":0,"section_name":"Introduction","source_file":null,"text":"We address the above problems by using paraphrases of the original question. Paraphrasing has shown to be promising for semantic parsing BIBREF9 , BIBREF10 , BIBREF11 . We propose a novel framework for paraphrasing using latent-variable PCFGs (L-PCFGs). Earlier approaches to paraphrasing used phrase-based machine translation for text-based QA BIBREF12 , BIBREF13 , or hand annotated grammars for KB-based QA BIBREF10 . We find that phrase-based statistical machine translation (MT) approaches mainly produce lexical paraphrases without much syntactic diversity, whereas our grammar-based approach is capable of producing both lexically and syntactically diverse paraphrases. Unlike MT based approaches, our system does not require aligned parallel paraphrase corpora. In addition we do not require hand annotated grammars for paraphrase generation but instead learn the grammar directly from a large scale question corpus."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:0:2","position":2,"section_index":0,"section_name":"Introduction","source_file":null,"text":"The main contributions of this paper are two fold. First, we present an algorithm (§ \"Paraphrase Generation Using Grammars\" ) to generate paraphrases using latent-variable PCFGs. We use the spectral method of narayan-15 to estimate L-PCFGs on a large scale question treebank. Our grammar model leads to a robust and an efficient system for paraphrase generation in open-domain question answering. While CFGs have been explored for paraphrasing using bilingual parallel corpus BIBREF14 , ours is the first implementation of CFG that uses only monolingual data. Second, we show that generated paraphrases can be used to improve semantic parsing of questions into Freebase logical forms (§ \"Semantic Parsing using Paraphrasing\" ). We build on a strong baseline of reddylargescale2014 and show that our grammar model competes with MT baseline even without using any parallel paraphrase resources."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:3:1","position":1,"section_index":3,"section_name":"Bi-Layered L-PCFGs","source_file":null,"text":"In their traditional use, the latent states in L-PCFGs aim to capture syntactic information. We introduce here the use of an L-PCFG with two layers of latent states: one layer is intended to capture the usual syntactic information, and the other aims to capture semantic and topical information by using a large set of states with specific feature functions."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:1:1","position":1,"section_index":1,"section_name":"Paraphrase Generation Using Grammars","source_file":null,"text":"In our estimation of L-PCFGs, we use the spectral method of narayan-15, instead of using EM, as has been used in the past by matsuzaki-2005 and petrov-2006. The spectral method we use enables the choice of a set of feature functions that indicate the latent states, which proves to be useful in our case. It also leads to sparse grammar estimates and compact models."}],"question":"What latent variables are modeled in the PCFG?","question_id":"ad362365656b0b218ba324ae60701eb25fe664c1"},{"paper_id":"1601.06068","passages":[{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:2:4","position":4,"section_index":2,"section_name":"Paraphrases Generation Algorithm","source_file":null,"text":"We train the L-PCFG $G_{\\mathrm {syn}}$ on the Paralex corpus BIBREF9 . Paralex is a large monolingual parallel corpus, containing 18 million pairs of question paraphrases with 2.4M distinct questions in the corpus. It is suitable for our task of generating paraphrases since its large scale makes our model robust for open-domain questions. We construct a treebank by parsing 2.4M distinct questions from Paralex using the BLLIP parser BIBREF25 ."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:4:0","position":0,"section_index":4,"section_name":"Paraphrase Classification","source_file":null,"text":"Our sampling algorithm overgenerates paraphrases which are incorrect. To improve its precision, we build a binary classifier to filter the generated paraphrases. We randomly select 100 distinct questions from the Paralex corpus and generate paraphrases using our generation algorithm with various lattice settings. We randomly select 1,000 pairs of input-sampled sentences and manually annotate them as “correct” or “incorrect” paraphrases. We train our classifier on this manually created training data. We follow madnani2012, who used MT metrics for paraphrase identification, and experiment with 8 MT metrics as features for our binary classifier. In addition, we experiment with a binary feature which checks if the sampled paraphrase preserves named entities from the input sentence. We use WEKA BIBREF32 to replicate the classifier of madnani2012 with our new feature. We tune the feature set for our classifier on the development data."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:11:1","position":1,"section_index":11,"section_name":"Baselines","source_file":null,"text":"We compare our paraphrasing models with monolingual machine translation based model for paraphrase generation BIBREF24 , BIBREF36 . In particular, we use Moses BIBREF37 to train a monolingual phrase-based MT system on the Paralex corpus. Finally, we use Moses decoder to generate 10-best distinct paraphrases for the test questions."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:12:0","position":0,"section_index":12,"section_name":"Implementation Details","source_file":null,"text":"For WebQuestions, we use 8 handcrafted part-of-speech patterns (e.g., the pattern (DT)?(JJ.? $\\mid $ NN.?){0,2}NN.? matches the noun phrase the big lebowski) to identify candidate named entity mention spans. We use the Stanford CoreNLP caseless tagger for part-of-speech tagging BIBREF38 . For each candidate mention span, we retrieve the top 10 entities according to the Freebase API. We then create a lattice in which the nodes correspond to mention-entity pairs, scored by their Freebase API scores, and the edges encode the fact that no joint assignment of entities to mentions can contain overlapping spans. We take the top 10 paths through the lattice as possible entity disambiguations. For each possibility, we generate $n$ -best paraphrases that contains the entity mention spans. In the end, this process creates a total of $10n$ paraphrases. We generate ungrounded graphs for these paraphrases and treat the final entity disambiguation and paraphrase selection as part of the semantic parsing problem."},{"kind":"paragraph","paper_id":"1601.06068","passage_id":"1601.06068:paragraph:3:3","position":3,"section_index":3,"section_name":"Bi-Layered L-PCFGs","source_file":null,"text":"Once the two feature functions (syntactic in $G_{\\mathrm {syn}}$ and semantic in $G_{\\mathrm {par}}$ ) are created, each nonterminal in the training treebank is assigned two latent states (cluster identifiers). Figure 2 shows an example annotation of trees for three paraphrase questions from the Paralex corpus. We compute the parameters of the bi-layered L-PCFG $G_{\\mathrm {layered}}$ with a simple frequency count maximum likelihood estimate over this annotated treebank. As such, $G_{\\mathrm {layered}}$ is a combination of $G_{\\mathrm {syn}}$ and $G_{\\mathrm {par}}$ , resulting in 24,000 latent states (24 syntactic x 1000 semantic)."}],"question":"How many paraphrases are generated per question?","question_id":"c359ab8ebef6f60c5a38f5244e8c18d85e92761d"},{"paper_id":"1601.06081","passages":[{"kind":"paragraph","paper_id":"1601.06081","passage_id":"1601.06081:paragraph:5:5","position":5,"section_index":5,"section_name":"Classification Experiments","source_file":null,"text":"Three Class Classification. Finally we also tested feature predictivity on a three class classification task (UL vs GN vs FT). Since in this case we did not performed downsampling, we use the ZeroR classifier as a baseline. For the sake of interpretability of results, along with precision, recall and F1 we also provide the Matthews Correlation Coefficient (MCC) which is useful for unbalanced datasets, as presented in BIBREF39 for the multiclass case. MCC returns a value between -1 and +1, where +1 represents a perfect prediction, 0 no better than random and -1 indicates total disagreement. Results are consistent with previous experiments. In Table 8 , all feature configurations show an improvement over the baseline ( $p<0.001$ ) but the temporal features (TIMEX) have far lower discriminative power as compared to others groups of features (MCC=0.339)."},{"kind":"paragraph","paper_id":"1601.06081","passage_id":"1601.06081:paragraph:7:2","position":2,"section_index":7,"section_name":"Ecological Experiments in the News Domain","source_file":null,"text":"Also in this case our features are able to discriminate between reliable and non-reliable stories (namely those coming from NYT and WWN). In particular, all the features together performed very well (F1 = 0.864), improving over all other subgroups of features (p $<$ 0.001), and NE, TIMEX, READ performed equally well improving over AFF that was the least effective (p $<$ 0.001). Still, AFF improves over the random baseline (p $<$ 0.001)."},{"kind":"paragraph","paper_id":"1601.06081","passage_id":"1601.06081:paragraph:4:5","position":5,"section_index":4,"section_name":"Descriptive Statistics","source_file":null,"text":"Turning to the analysis of variance, we see that FT is – on average – a more cohesive genre, with lower standard deviations, while GN and UL have higher and closer standard deviations. In fact, all differences in the standard deviations reported in the tables are statistically significant (f-test, $p<0.001$ ) apart between UL and GN in Fog, Kincaid and in ALL sentiment (signalled with * in the respective Tables)."},{"kind":"paragraph","paper_id":"1601.06081","passage_id":"1601.06081:paragraph:5:3","position":3,"section_index":5,"section_name":"Classification Experiments","source_file":null,"text":"In Table 7 we report the performances of the various classification tasks in term of precision, recall and F1 over the single classes. Interestingly, for almost all feature combinations the classifiers had slightly higher precision than recall for UL, while the contrary holds for FT and GN."},{"kind":"paragraph","paper_id":"1601.06081","passage_id":"1601.06081:paragraph:5:4","position":4,"section_index":5,"section_name":"Classification Experiments","source_file":null,"text":"News vs Fairy Tales. Finally, we wanted to check whether UL being “half-way\" between GN and FT can be observed in our classification experiments as well. If this hypothesis is correct, by classifying GN vs. FT we would expect to find higher performance than previous experiments. Results show that this is in fact the case. All features together performed better than all previous experiment and incredibly well (F1= 0.978), again improving over all the other subgroups of features alone ( $p<0.001$ ) apart from READ that performs equally well (F1=0.973, no statistically significant difference). Notably, all other groups of features improves over the UL vs. GN and the UL vs. FT tasks. Finally, all groups of features had a statistically significant improvement over the random baseline ( $p<0.001$ )."}],"question":"How accurate is their predictive model?","question_id":"6f8881e60fdaca7c1b35a5acc7125994bb1206a3"},{"paper_id":"1601.06738","passages":[{"kind":"paragraph","paper_id":"1601.06738","passage_id":"1601.06738:paragraph:0:3","position":3,"section_index":0,"section_name":"Introduction","source_file":null,"text":"In the following we provide an account of linguistic hedges that is both functional, and semantically grounded. In its most basic formulation, the operation requires no additional parameters, although we also show that the formulae can be generalised if necessary. Our account of linguistic hedges uses the label semantics framework to model concepts BIBREF12 . This is a random set approach which quantifies an agent's subjective uncertainty about the extent of application of a concept. We refer to this uncertainty as semantic uncertainty BIBREF13 to emphasise that it concerns the definition of concepts and categories, in contrast to stochastic uncertainty which concerns the state of the world. In BIBREF13 the label semantics approach is combined with conceptual spaces BIBREF14 and prototype theory BIBREF15 , to give a formalisation of concepts as based on a prototype and a threshold, located in a conceptual space. This approach is discussed in detail in section \"Conceptual Spaces\" . An outline of the paper is then as follows: section \"Approaches to linguistic hedges\" discusses different approaches to linguistic hedges from the literature, and compares these with our model. Subsequently, in section \"Label semantics approach to linguistic hedges\" , we give formulations of the hedges `very' and `quite'. These are formed by considering the dependence of the threshold of a hedged concept on the threshold of the original concept. We give a basic model and two generalisations, show that the models can be composed and investigate the behaviour in the limit of composition. Section \"Discussion\" compares our results to those in the literature and proposes further lines of research."},{"kind":"paragraph","paper_id":"1601.06738","passage_id":"1601.06738:paragraph:4:0","position":0,"section_index":4,"section_name":"Approaches to linguistic hedges","source_file":null,"text":"Linguistic hedges have been given varying treatments in the literature. In this section we summarise these different approaches and state the approach that we wish to take, discussing properties that hedge modifiers may need. We give two specific approaches from the literature with which we will compare our results."},{"kind":"paragraph","paper_id":"1601.06738","passage_id":"1601.06738:paragraph:6:10","position":10,"section_index":6,"section_name":"Hedges with unmodified prototypes","source_file":null,"text":"The effect of these hedges are illustrated in the following example."},{"kind":"paragraph","paper_id":"1601.06738","passage_id":"1601.06738:paragraph:6:12","position":12,"section_index":6,"section_name":"Hedges with unmodified prototypes","source_file":null,"text":"These hedges can also be applied across multiple dimensions, demonstrated in the example below."},{"kind":"paragraph","paper_id":"1601.06738","passage_id":"1601.06738:paragraph:12:0","position":0,"section_index":12,"section_name":"Discussion","source_file":null,"text":"We have presented formulae for linguistic hedges which are both functional and semantically grounded. The modifiers presented arise naturally from the label semantics framework, in which concepts are represented by a prototype and threshold. Our hedges have an intuitive meaning: if I think that the threshold for a concept `small' is of a certain width, then the threshold for the concept `very small' will be narrower. On the other hand, the threshold for the concept `quite small' will be broader. The hedges proposed are examples of `type 1' hedges, i.e. they operate equally across all dimensions of the fuzzy set associated with a concept. The first result presented is somewhat similar to a powering modifier since the core and support of the set remain the same. In BIBREF9 , BIBREF7 , it is argued that this property is undesirable for hedges used in fuzzy expert systems, since if a query is returning too large a set of answers, this type of contraction hedge does not reduce this overabundance. However, although the hedges we propose do not at their simplest address the overabundance issue, we argue that they address another problem associated with powering hedges, in that they have a clear semantic grounding that the powering modifiers lack."}],"question":"Does this paper address the variation among English dialects regarding these hedges?","question_id":"320d72a9cd19b52c29dda9ddecd520c9938a717f"},{"paper_id":"1602.00812","passages":[{"kind":"abstract","paper_id":"1602.00812","passage_id":"1602.00812:abstract:0","position":0,"section_index":null,"section_name":"Abstract","source_file":null,"text":"As the name suggests, type-logical grammars are a grammar formalism based on logic and type theory. From the prespective of grammar design, type-logical grammars develop the syntactic and semantic aspects of linguistic phenomena hand-in-hand, letting the desired semantics of an expression inform the syntactic type and vice versa. Prototypical examples of the successful application of type-logical grammars to the syntax-semantics interface include coordination, quantifier scope and extraction.This chapter describes the Grail theorem prover, a series of tools for designing and testing grammars in various modern type-logical grammars which functions as a tool . All tools described in this chapter are freely available."},{"kind":"paragraph","paper_id":"1602.00812","passage_id":"1602.00812:paragraph:10:26","position":26,"section_index":10,"section_name":"Multimodal proof nets","source_file":null,"text":"As to the proof search strategy used by Grail, it is an instance of the “dancing links” algorithm BIBREF35 : when connecting atomic formulas, we always link a formula which has the least possibilities and we rewrite the abstract proof structures only once a fully linked proof structure has been produced. Though the parser is not extremely fast, evaluation both on randomly generated statements and on multimodal statements extracted from corpora show that the resulting algorithm performs more than well enough BIBREF36 ."},{"kind":"paragraph","paper_id":"1602.00812","passage_id":"1602.00812:paragraph:10:24","position":24,"section_index":10,"section_name":"Multimodal proof nets","source_file":null,"text":"As a compromise between efficiency and flexibility, Grail allows the grammar writer to specify a first-order approximation of her structural rules. Unlike the test for validity in multiplicative linear logic which is valid for any set of structural rules, specifying such a first-order approximation is valid only when there is a guarantee that all derivable sequents in the multimodal grammar are a subset of their approximations derivable in first-order linear logic. Errors made here can be rather subtle and hard to detect. It is recommended to use such methods to improve parsing speed only when a grammar has been sufficiently tested and where it is possible to verify whether no valid readings are excluded, or, ideally, to prove that the subset relation holds between the multimodal logic and its first-order approximation."},{"kind":"paragraph","paper_id":"1602.00812","passage_id":"1602.00812:paragraph:0:0","position":0,"section_index":0,"section_name":"Introduction","source_file":null,"text":"This chapter describes a series of tools for developing and testing type-logical grammars. The Grail family of theorem provers have been designed to work with a variety of modern type-logical frameworks, including multimodal type-logical grammars BIBREF0 , NL $_{cl}$ BIBREF1 , the Displacement calculus BIBREF2 and hybrid type-logical grammars BIBREF3 ."},{"kind":"paragraph","paper_id":"1602.00812","passage_id":"1602.00812:paragraph:12:0","position":0,"section_index":12,"section_name":"Tools","source_file":null,"text":"Table 9 lists the different theorem provers which are available. Grail 0 BIBREF42 and Grail 3 BIBREF43 use the multimodal proof net calculus of Section \"Multimodal proof nets\" , whereas LinearOne BIBREF44 uses the first-order proof nets of Section \"First-order proof nets\" . GrailLight BIBREF45 is a special-purpose chart parser, intended for use with an automatically extracted French grammar for wide-coverage parsing and semantics BIBREF34 , BIBREF46 . All provers are provided under the GNU Lesser General Public License — this means, notably, there is no warranty, though I am committed to making all software as useful as possible; so contact me for any comments, feature requests or bug reports. All theorem provers can be downloaded from the author's GitHub site."}],"question":"What formalism does Grail use?","question_id":"2b52d481b30185d2c6e7b403d37277f70337d6ca"},{"paper_id":"1602.00812","passages":[{"kind":"paragraph","paper_id":"1602.00812","passage_id":"1602.00812:paragraph:10:24","position":24,"section_index":10,"section_name":"Multimodal proof nets","source_file":null,"text":"As a compromise between efficiency and flexibility, Grail allows the grammar writer to specify a first-order approximation of her structural rules. Unlike the test for validity in multiplicative linear logic which is valid for any set of structural rules, specifying such a first-order approximation is valid only when there is a guarantee that all derivable sequents in the multimodal grammar are a subset of their approximations derivable in first-order linear logic. Errors made here can be rather subtle and hard to detect. It is recommended to use such methods to improve parsing speed only when a grammar has been sufficiently tested and where it is possible to verify whether no valid readings are excluded, or, ideally, to prove that the subset relation holds between the multimodal logic and its first-order approximation."},{"kind":"paragraph","paper_id":"1602.00812","passage_id":"1602.00812:paragraph:0:0","position":0,"section_index":0,"section_name":"Introduction","source_file":null,"text":"This chapter describes a series of tools for developing and testing type-logical grammars. The Grail family of theorem provers have been designed to work with a variety of modern type-logical frameworks, including multimodal type-logical grammars BIBREF0 , NL $_{cl}$ BIBREF1 , the Displacement calculus BIBREF2 and hybrid type-logical grammars BIBREF3 ."},{"kind":"caption","paper_id":"1602.00812","passage_id":"1602.00812:caption:14","position":14,"section_index":null,"section_name":"Figures and tables","source_file":"24-Figure9.11-1.png","text":"Fig. 9.11 Interactive Grail output"},{"kind":"paragraph","paper_id":"1602.00812","passage_id":"1602.00812:paragraph:12:0","position":0,"section_index":12,"section_name":"Tools","source_file":null,"text":"Table 9 lists the different theorem provers which are available. Grail 0 BIBREF42 and Grail 3 BIBREF43 use the multimodal proof net calculus of Section \"Multimodal proof nets\" , whereas LinearOne BIBREF44 uses the first-order proof nets of Section \"First-order proof nets\" . GrailLight BIBREF45 is a special-purpose chart parser, intended for use with an automatically extracted French grammar for wide-coverage parsing and semantics BIBREF34 , BIBREF46 . All provers are provided under the GNU Lesser General Public License — this means, notably, there is no warranty, though I am committed to making all software as useful as possible; so contact me for any comments, feature requests or bug reports. All theorem provers can be downloaded from the author's GitHub site."},{"kind":"paragraph","paper_id":"1602.00812","passage_id":"1602.00812:paragraph:10:26","position":26,"section_index":10,"section_name":"Multimodal proof nets","source_file":null,"text":"As to the proof search strategy used by Grail, it is an instance of the “dancing links” algorithm BIBREF35 : when connecting atomic formulas, we always link a formula which has the least possibilities and we rewrite the abstract proof structures only once a fully linked proof structure has been produced. Though the parser is not extremely fast, evaluation both on randomly generated statements and on multimodal statements extracted from corpora show that the resulting algorithm performs more than well enough BIBREF36 ."}],"question":"Does Grail accept Prolog inputs?","question_id":"48fa2ccc236e217fcf0e5aab0e7a146faf439b02"},{"paper_id":"1602.01208","passages":[{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:2:1","position":1,"section_index":2,"section_name":"Simultaneous learning of places and vocabulary","source_file":null,"text":"Taguchi et al. proposed a method for the unsupervised learning of phoneme sequences and relationships between words and objects from various user utterances without any prior linguistic knowledge other than an acoustic model of phonemes BIBREF1 , BIBREF14 . Further, they proposed a method for the simultaneous categorization of self-position coordinates and lexical learning BIBREF15 . These experimental results showed that it was possible to learn the name of a place from utterances in some cases and to output words corresponding to places in a location that was not used for learning."},{"kind":"abstract","paper_id":"1602.01208","passage_id":"1602.01208:abstract:0","position":0,"section_index":null,"section_name":"Abstract","source_file":null,"text":"In this paper, we propose a novel unsupervised learning method for the lexical acquisition of words related to places visited by robots, from human continuous speech signals. We address the problem of learning novel words by a robot that has no prior knowledge of these words except for a primitive acoustic model. Further, we propose a method that allows a robot to effectively use the learned words and their meanings for self-localization tasks. The proposed method is nonparametric Bayesian spatial concept acquisition method (SpCoA) that integrates the generative model for self-localization and the unsupervised word segmentation in uttered sentences via latent variables related to the spatial concept. We implemented the proposed method SpCoA on SIGVerse, which is a simulation environment, and TurtleBot2, which is a mobile robot in a real environment. Further, we conducted experiments for evaluating the performance of SpCoA. The experimental results showed that SpCoA enabled the robot to acquire the names of places from speech sentences. They also revealed that the robot could effectively utilize the acquired spatial concepts and reduce the uncertainty in self-localization."},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:0:1","position":1,"section_index":0,"section_name":"Introduction","source_file":null,"text":"Several studies on language acquisition by robots have assumed that robots have no prior lexical knowledge. These studies differ from speech recognition studies based on a large vocabulary and natural language processing studies based on lexical, syntactic, and semantic knowledge BIBREF0 , BIBREF1 . Studies on language acquisition by robots also constitute a constructive approach to the human developmental process and the emergence of symbols."},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:0:2","position":2,"section_index":0,"section_name":"Introduction","source_file":null,"text":"The objectives of this study were to build a robot that learns words related to places and efficiently utilizes this learned vocabulary in self-localization. Lexical acquisition related to places is expected to enable a robot to improve its spatial cognition. A schematic representation depicting the target task of this study is shown in Fig. FIGREF3 . This study assumes that a robot does not have any vocabularies in advance but can recognize syllables or phonemes. The robot then performs self-localization while moving around in the environment, as shown in Fig. FIGREF3 (a). An utterer speaks a sentence including the name of the place to the robot, as shown in Fig. FIGREF3 (b). For the purposes of this study, we need to consider the problems of self-localization and lexical acquisition simultaneously."},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:1:1","position":1,"section_index":1,"section_name":"Lexical acquisition","source_file":null,"text":"Roy et al. proposed a computational model that enables a robot to learn the names of objects from an object image and spontaneous infant-directed speech BIBREF0 . Their results showed that the model performed speech segmentation, word discovery, and visual categorization. Iwahashi et al. reported that a robot properly understands the situation and acquires the relationship of object behaviors and sentences BIBREF2 , BIBREF3 , BIBREF4 . Qu & Chai focused on the conjunction between speech and eye gaze and the use of domain knowledge in lexical acquisition BIBREF6 , BIBREF7 . They proposed an unsupervised learning method that automatically acquires novel words for an interactive system. Qu & Chai's method based on the IBM translation model BIBREF11 estimates the word-entity association probability."}],"question":"Does their model start with any prior knowledge of words?","question_id":"1bdf7e9f3f804930b2933ebd9207a3e000b27742"},{"paper_id":"1602.01208","passages":[{"kind":"abstract","paper_id":"1602.01208","passage_id":"1602.01208:abstract:0","position":0,"section_index":null,"section_name":"Abstract","source_file":null,"text":"In this paper, we propose a novel unsupervised learning method for the lexical acquisition of words related to places visited by robots, from human continuous speech signals. We address the problem of learning novel words by a robot that has no prior knowledge of these words except for a primitive acoustic model. Further, we propose a method that allows a robot to effectively use the learned words and their meanings for self-localization tasks. The proposed method is nonparametric Bayesian spatial concept acquisition method (SpCoA) that integrates the generative model for self-localization and the unsupervised word segmentation in uttered sentences via latent variables related to the spatial concept. We implemented the proposed method SpCoA on SIGVerse, which is a simulation environment, and TurtleBot2, which is a mobile robot in a real environment. Further, we conducted experiments for evaluating the performance of SpCoA. The experimental results showed that SpCoA enabled the robot to acquire the names of places from speech sentences. They also revealed that the robot could effectively utilize the acquired spatial concepts and reduce the uncertainty in self-localization."},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:1:1","position":1,"section_index":1,"section_name":"Lexical acquisition","source_file":null,"text":"Roy et al. proposed a computational model that enables a robot to learn the names of objects from an object image and spontaneous infant-directed speech BIBREF0 . Their results showed that the model performed speech segmentation, word discovery, and visual categorization. Iwahashi et al. reported that a robot properly understands the situation and acquires the relationship of object behaviors and sentences BIBREF2 , BIBREF3 , BIBREF4 . Qu & Chai focused on the conjunction between speech and eye gaze and the use of domain knowledge in lexical acquisition BIBREF6 , BIBREF7 . They proposed an unsupervised learning method that automatically acquires novel words for an interactive system. Qu & Chai's method based on the IBM translation model BIBREF11 estimates the word-entity association probability."},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:4:1","position":1,"section_index":4,"section_name":"Generative model","source_file":null,"text":"The model that was developed for spatial concept acquisition is a probabilistic generative model that integrates a self-localization with the simultaneous clustering of places and words. Fig. FIGREF13 shows the graphical model for spatial concept acquisition. Table TABREF14 shows each variable of the graphical model. The number of words in a sentence at time INLINEFORM0 is denoted as INLINEFORM1 . The generative model of the proposed method is defined as equation ( EQREF11 -). DISPLAYFORM0 "},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:0:5","position":5,"section_index":0,"section_name":"Introduction","source_file":null,"text":"In this paper, we propose nonparametric Bayesian spatial concept acquisition method (SpCoA) on basis of unsupervised word segmentation and a nonparametric Bayesian generative model that integrates self-localization and a clustering in both words and places. The main contributions of this paper are as follows:"},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:11:1","position":1,"section_index":11,"section_name":"Estimation accuracy of spatial concepts","source_file":null,"text":"Further, we compared the proposed method with a method of word clustering without location information for the investigation of the effect of lexical acquisition using location information. In particular, a method of word clustering without location information used the Dirichlet process mixture (DPM) of the unigram model of an SBP representation. The parameters corresponding to those of the proposed method were the same as the parameters of the proposed method and were estimated using Gibbs sampling."}],"question":"How do they evaluate how their model acquired words?","question_id":"21c104d14ba3db7fe2cd804a191f9e6258208235"},{"paper_id":"1602.01208","passages":[{"kind":"abstract","paper_id":"1602.01208","passage_id":"1602.01208:abstract:0","position":0,"section_index":null,"section_name":"Abstract","source_file":null,"text":"In this paper, we propose a novel unsupervised learning method for the lexical acquisition of words related to places visited by robots, from human continuous speech signals. We address the problem of learning novel words by a robot that has no prior knowledge of these words except for a primitive acoustic model. Further, we propose a method that allows a robot to effectively use the learned words and their meanings for self-localization tasks. The proposed method is nonparametric Bayesian spatial concept acquisition method (SpCoA) that integrates the generative model for self-localization and the unsupervised word segmentation in uttered sentences via latent variables related to the spatial concept. We implemented the proposed method SpCoA on SIGVerse, which is a simulation environment, and TurtleBot2, which is a mobile robot in a real environment. Further, we conducted experiments for evaluating the performance of SpCoA. The experimental results showed that SpCoA enabled the robot to acquire the names of places from speech sentences. They also revealed that the robot could effectively utilize the acquired spatial concepts and reduce the uncertainty in self-localization."},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:0:4","position":4,"section_index":0,"section_name":"Introduction","source_file":null,"text":"In order to solve the abovementioned problems, in this study, we adopted the following approach. An utterance is recognized as not a single phoneme sequence but a set of candidates of multiple phonemes. We attempt to suppress the variability in the speech recognition results by performing word discovery taking into account the multiple candidates of speech recognition. In addition, the names of places are learned by associating with words and positions. The lexical acquisition is complemented by using certain particular spatial information; i.e., this information is obtained by hearing utterances including the same word in the same place many times. Furthermore, in this study, we attempt to address the problem of the uncertainty of self-localization by improving the self-position errors by using a recognized utterance including the name of the current place and the acquired spatial concepts, as shown in Fig. FIGREF3 (e)."},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:8:2","position":2,"section_index":8,"section_name":"Experiment I","source_file":null,"text":"The remainder of this section is organized as follows: In Section SECREF43 , the conditions and results of learning spatial concepts are described. The experiments performed using the learned spatial concepts are described in Section SECREF49 to SECREF64 . In Section SECREF49 , we evaluate the accuracy of the phoneme recognition and word segmentation for uttered sentences. In Section SECREF56 , we evaluate the clustering accuracy of the estimation results of index INLINEFORM0 of spatial concepts for each teaching utterance. In Section SECREF60 , we evaluate the accuracy of the acquisition of names of places. In Section SECREF64 , we show that spatial concepts can be utilized for effective self-localization."},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:0:2","position":2,"section_index":0,"section_name":"Introduction","source_file":null,"text":"The objectives of this study were to build a robot that learns words related to places and efficiently utilizes this learned vocabulary in self-localization. Lexical acquisition related to places is expected to enable a robot to improve its spatial cognition. A schematic representation depicting the target task of this study is shown in Fig. FIGREF3 . This study assumes that a robot does not have any vocabularies in advance but can recognize syllables or phonemes. The robot then performs self-localization while moving around in the environment, as shown in Fig. FIGREF3 (a). An utterer speaks a sentence including the name of the place to the robot, as shown in Fig. FIGREF3 (b). For the purposes of this study, we need to consider the problems of self-localization and lexical acquisition simultaneously."},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:16:1","position":1,"section_index":16,"section_name":"Modification of localization by the acquired spatial concepts","source_file":null,"text":"Fig. FIGREF80 shows the results of the self-localization before (the top part of the figure) and after (the bottom part of the figure) the utterance for three places. The particle states are denoted by red arrows. The moving trajectory of the robot is indicated by a green dotted arrow. Figs. FIGREF80 (a), (b), and (c) show the results for the names of places “toire”, “souhatsukeN”, and “gomibako”. Further, three spatial concepts, i.e., those at INLINEFORM0 , were learned as “gomibako”. In this experiment, the utterer uttered to the robot when the robot came close to the place of INLINEFORM1 . In all the examples shown in the top part of the figure, the particles were dispersed in several places. In contrast, the number of particles near the true position of the robot showed an almost accurate increase in all the examples shown in the bottom part of the figure. Thus, we can conclude that the proposed method can modify self-localization by using spatial concepts."}],"question":"How do they show that acquiring names of places helps self-localization?","question_id":"23d0637f8ae72ae343556ab135eedc7f4cb58032"},{"paper_id":"1602.01208","passages":[{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:5:3","position":3,"section_index":5,"section_name":"Overview of the proposed method SpCoA","source_file":null,"text":"Word segmentation is performed by using the lattices of the speech recognition results."},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:10:2","position":2,"section_index":10,"section_name":"Phoneme recognition accuracy of uttered sentences","source_file":null,"text":"Table TABREF54 shows the results of PAR. Table TABREF55 presents examples of the word segmentation results of the three considered methods. We found that the unsupervised morphological analyzer capable of using lattices improved the accuracy of phoneme recognition and word segmentation. Consequently, this result suggests that this word segmentation method considers the multiple hypothesis of speech recognition as a whole and reduces uncertainty such as variability in recognition by using the syllable recognition results in the lattice format."},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:5:9","position":9,"section_index":5,"section_name":"Overview of the proposed method SpCoA","source_file":null,"text":"The proposed method can learn words related to places from the utterances of sentences. We use an unsupervised word segmentation method latticelm that can directly segment words from the lattices of the speech recognition results of the uttered sentences BIBREF22 . The lattice can represent to a compact the set of more promising hypotheses of a speech recognition result, such as N-best, in a directed graph format. Unsupervised word segmentation using the lattices of syllable recognition is expected to be able to reduce the variability and errors in phonemes as compared to NPYLM BIBREF13 , i.e., word segmentation using the 1-best speech recognition results."},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:8:1","position":1,"section_index":8,"section_name":"Experiment I","source_file":null,"text":"In the experiment, we compare the following three types of word segmentation methods. A set of syllable sequences is given to the graphical model of SpCoA by each method. This set is used for the learning of spatial concepts as recognized uttered sentences INLINEFORM0 ."},{"kind":"paragraph","paper_id":"1602.01208","passage_id":"1602.01208:paragraph:0:5","position":5,"section_index":0,"section_name":"Introduction","source_file":null,"text":"In this paper, we propose nonparametric Bayesian spatial concept acquisition method (SpCoA) on basis of unsupervised word segmentation and a nonparametric Bayesian generative model that integrates self-localization and a clustering in both words and places. The main contributions of this paper are as follows:"}],"question":"Which method do they use for word segmentation?","question_id":"d557752c4706b65dcdb7718272180c59d77fb7a7"}],"scores_sha256":"a75cce0955837f824f009cdf3eda7bd40621f636248d0a5ce47c417393f1ae98","sha256":"3529a49451fb4bd791167a6d0be4088c95004ab34c02dc6e7dd24b28b2b33231"}