[{"annotations":[{"annotation_id":"2ad8a8c4827f8617a9f38d243b56a2adb3518ba5","answer_type":"extractive","evidence":["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."],"extractive_spans":["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"],"free_form_answer":"","unanswerable":false,"yes_no":null}],"paper_id":"1601.00901","question":"How did they induce the CFG?","question_id":"74b0d3ee0cc9b0a3d9b264aba9901ff97048a897"},{"annotations":[{"annotation_id":"5cd39c20891ea9876f10018e07223969332a4dfb","answer_type":"extractive","evidence":["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.","There are 119 different relation types (unique predicates), having from just a few relations to a few million relations. Since DBpedia and Freebase are available in RDF format, we used the RDF store for querying and for storage of existing and new relations."],"extractive_spans":["1.1 million sentences","119 different relation types (unique predicates)"],"free_form_answer":"","unanswerable":false,"yes_no":null}],"paper_id":"1601.00901","question":"How big is their dataset?","question_id":"9eb5b336b3dcb7ab63f673ba9ab1818573cce6c3"},{"annotations":[{"annotation_id":"46e5ea281159cbd3c2de92d958a1f2a835593916","answer_type":"free_form","evidence":["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.","The next set of experiments we consider focuses on GeoQA, a geographical question-answering task first introduced by Krish2013Grounded. This task was originally paired with a visual question answering task much simpler than the one just discussed, and is appealing for a number of reasons. In contrast to the VQA dataset, GeoQA is quite small, containing only 263 examples. Two baselines are available: one using a classical semantic parser backed by a database, and another which induces logical predicates using linear classifiers over both spatial and distributional features. This allows us to evaluate the quality of our model relative to other perceptually grounded logical semantics, as well as strictly logical approaches."],"extractive_spans":[],"free_form_answer":"VQA and GeoQA","unanswerable":false,"yes_no":null}],"paper_id":"1601.01705","question":"What benchmark datasets they use?","question_id":"5712a0b1e33484ebc6d71c70ae222109c08dede2"},{"annotations":[{"annotation_id":"242af0098d4f61a8d54d7f9225e27a11d1652f95","answer_type":"unanswerable","evidence":[],"extractive_spans":[],"free_form_answer":"","unanswerable":true,"yes_no":null}],"paper_id":"1601.02166","question":"What languages did they experiment with?","question_id":"e67d2266476abd157fc8c396b3dfb70cb343471e"},{"annotations":[{"annotation_id":"40e8b561276384d47c4e6a0d3861d502b1fe37f3","answer_type":"free_form","evidence":["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.","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."],"extractive_spans":[],"free_form_answer":"Confusion in recognizing the words that are active at a given node by a speech recognition solution developed for Indian Railway Inquiry System.","unanswerable":false,"yes_no":null}],"paper_id":"1601.02543","question":"what bottlenecks were identified?","question_id":"8d793bda51a53a4605c1c33e7fd20ba35581a518"},{"annotations":[{"annotation_id":"d7488554bc89783a43fe78b62c5890a9fc7b8d4a","answer_type":"extractive","evidence":["There have been several workshops on biomedical natural language processing. We focus on the BioNLP Shared Tasks in recent years that had competitions on event extraction. There have been three BioNLP Shared Task competitions so far: 2009, 2011, and 2013. The BioNLP 2009 Shared Task BIBREF195 was based on the GENIA corpus BIBREF196 which contains PubMed abstracts of articles on transcription factors in human blood cells. There was a second BioNLP Shared Task competition organized in 2011 to measure the advances in approaches and associated results BIBREF197 . The third BioNLP ST was held in 2013. We discuss some notable systems from BioNLP ST 2011 and 2013."],"extractive_spans":["GENIA corpus"],"free_form_answer":"","unanswerable":false,"yes_no":null}],"paper_id":"1601.04012","question":"Which datasets are used in this work?","question_id":"eac042734f76e787cb98ba3d0c13a916a49bdfb3"},{"annotations":[{"annotation_id":"208951f0d5f93c878368122d70fd94c337104a5e","answer_type":"yes_no","evidence":[],"extractive_spans":[],"free_form_answer":"","unanswerable":false,"yes_no":false}],"paper_id":"1601.06068","question":"Do they evaluate the quality of the paraphrasing model?","question_id":"117aa7811ed60e84d40cd8f9cb3ca78781935a98"},{"annotations":[{"annotation_id":"32749f613e7b20e5fde56cfe720b1ecddf2646ff","answer_type":"extractive","evidence":["We use GraphParser without paraphrases as our baseline. This gives an idea about the impact of using paraphrases.","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."],"extractive_spans":["GraphParser without paraphrases","monolingual machine translation based model for paraphrase generation"],"free_form_answer":"","unanswerable":false,"yes_no":null}],"paper_id":"1601.06068","question":"What are the baselines?","question_id":"423bb905e404e88a168e7e807950e24ca166306c"},{"annotations":[{"annotation_id":"727ec6309fb3d7beb4d8cf4455fe5c4778bb660e","answer_type":"extractive","evidence":["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."],"extractive_spans":["syntactic information","semantic and topical information"],"free_form_answer":"","unanswerable":false,"yes_no":null}],"paper_id":"1601.06068","question":"What latent variables are modeled in the PCFG?","question_id":"ad362365656b0b218ba324ae60701eb25fe664c1"},{"annotations":[{"annotation_id":"12f2e670e6d94fab6636a8ef24121fc2f2100eeb","answer_type":"free_form","evidence":["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."],"extractive_spans":[],"free_form_answer":"10*n paraphrases, where n depends on the number of paraphrases that contain the entity mention spans","unanswerable":false,"yes_no":null}],"paper_id":"1601.06068","question":"How many paraphrases are generated per question?","question_id":"c359ab8ebef6f60c5a38f5244e8c18d85e92761d"},{"annotations":[{"annotation_id":"9b225953b4d627b8e6eac36e4721273a60f91e3c","answer_type":"unanswerable","evidence":[],"extractive_spans":[],"free_form_answer":"","unanswerable":true,"yes_no":null}],"paper_id":"1601.06081","question":"How accurate is their predictive model?","question_id":"6f8881e60fdaca7c1b35a5acc7125994bb1206a3"},{"annotations":[{"annotation_id":"aba922a2695a5c7602e5e59bed9fda244f5ada81","answer_type":"yes_no","evidence":[],"extractive_spans":[],"free_form_answer":"","unanswerable":false,"yes_no":false}],"paper_id":"1601.06738","question":"Does this paper address the variation among English dialects regarding these hedges?","question_id":"320d72a9cd19b52c29dda9ddecd520c9938a717f"},{"annotations":[{"annotation_id":"5e88fc881a24ca113fe7cc075f1587f1f94dea24","answer_type":"extractive","evidence":["This chapter describes the underlying formalism of the theorem provers, as it is visible during an interactive proof trace, and present the general strategy followed by the theorem provers. The presentation in this chapter is somewhat informal, referring the reader elsewhere for full proofs.","The rest of this chapter is structured as follows. Section \"Type-logical grammars\" presents a general introduction to type-logical grammars and illustrates its basic concepts using the Lambek calculus, ending the section with some problems at the syntax-semantics interface for the Lambek calculus. Section \"Modern type-logical grammars\" looks at recent developments in type-logical grammars and how they solve some of the problems at the syntax-semantics interface. Section \"Theorem proving\" looks at two general frameworks for automated theorem proving for type-logical grammars, describing the internal representation of partial proofs and giving a high-level overview of the proof search mechanism.","Type-logical grammars are a family of grammar formalisms built on a foundation of logic and type theory. Type-logical grammars originated when BIBREF4 introduced his Syntactic Calculus (called the Lambek calculus, L, by later authors). Though Lambek built on the work of BIBREF5 , BIBREF6 and others, Lambek's main innovation was to cast the calculus as a logic, giving a sequent calculus and showing decidability by means of cut elimination. This combination of linguistic and computational applications has proved very influential."],"extractive_spans":["a family of grammar formalisms built on a foundation of logic and type theory. Type-logical grammars originated when BIBREF4 introduced his Syntactic Calculus (called the Lambek calculus, L, by later authors)."],"free_form_answer":"","unanswerable":false,"yes_no":null}],"paper_id":"1602.00812","question":"What formalism does Grail use?","question_id":"2b52d481b30185d2c6e7b403d37277f70337d6ca"},{"annotations":[{"annotation_id":"3e6e3d3968c8c45146719555aa0bdbdc1d73b04c","answer_type":"yes_no","evidence":["In its general form, a type-logical grammar consists of following components:"],"extractive_spans":[],"free_form_answer":"","unanswerable":false,"yes_no":false}],"paper_id":"1602.00812","question":"Does Grail accept Prolog inputs?","question_id":"48fa2ccc236e217fcf0e5aab0e7a146faf439b02"},{"annotations":[{"annotation_id":"ac643eb23016caf26384e4a5522dd1d90369d26e","answer_type":"yes_no","evidence":["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."],"extractive_spans":[],"free_form_answer":"","unanswerable":false,"yes_no":false}],"paper_id":"1602.01208","question":"Does their model start with any prior knowledge of words?","question_id":"1bdf7e9f3f804930b2933ebd9207a3e000b27742"},{"annotations":[{"annotation_id":"668d93e897fd33aa512ddb05558327e6dc536278","answer_type":"extractive","evidence":["Accuracy of acquired phoneme sequences representing the names of places","We evaluated whether the names of places were properly learned for the considered teaching places. This experiment assumes a request for the best phoneme sequence INLINEFORM0 representing the self-position INLINEFORM1 for a robot. The robot moves close to each teaching place. The probability of a word INLINEFORM2 when the self-position INLINEFORM3 of the robot is given, INLINEFORM4 , can be obtained by using equation ( EQREF37 ). The word having the best probability was selected. We compared the PAR with the correct phoneme sequence and a selected name of the place. Because “kiqchiN” and “daidokoro” were taught for the same place, the word whose PAR was the higher score was adopted.","Fig. FIGREF63 shows the results of PAR for the word considered the name of a place. SpCoA (latticelm), the proposed method using the results of unsupervised word segmentation on the basis of the speech recognition results in the lattice format, showed the best PAR score. In the 1-best and BoS methods, a part syllable sequence of the name of a place was more minutely segmented as shown in Table TABREF55 . Therefore, the robot could not learn the name of the teaching place as a coherent phoneme sequence. In contrast, the robot could learn the names of teaching places more accurately by using the proposed method."],"extractive_spans":["PAR score"],"free_form_answer":"","unanswerable":false,"yes_no":null}],"paper_id":"1602.01208","question":"How do they evaluate how their model acquired words?","question_id":"21c104d14ba3db7fe2cd804a191f9e6258208235"},{"annotations":[{"annotation_id":"9eea9f7b9f483c773699694e80da81d9f5fb9388","answer_type":"extractive","evidence":["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."],"extractive_spans":["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"],"free_form_answer":"","unanswerable":false,"yes_no":null}],"paper_id":"1602.01208","question":"How do they show that acquiring names of places helps self-localization?","question_id":"23d0637f8ae72ae343556ab135eedc7f4cb58032"},{"annotations":[{"annotation_id":"98c74c25f24acd3dd6220f4dd2310d4b84b2f823","answer_type":"extractive","evidence":["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."],"extractive_spans":["unsupervised word segmentation method latticelm"],"free_form_answer":"","unanswerable":false,"yes_no":null}],"paper_id":"1602.01208","question":"Which method do they use for word segmentation?","question_id":"d557752c4706b65dcdb7718272180c59d77fb7a7"}]