text
stringlengths
0
164k
<s>[INST] Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning [/INST] Taskoriented dialog systems help a user to accomplish some goal using natural language such as making a restaurant reservation getting technical support or placing a phonecall Historicall...
<s>[INST] Leveraging Recurrent Neural Networks for Multimodal Recognition of Social Norm Violation in Dialog [/INST] Social norms are informal understandings that govern human behavior They serve as the basis for our beliefs and expectations about others and are instantiated in humanhuman conversation through verbal an...
left
beginmatrix
it
ft
ot
jt
endmatrix
right
left
beginmatrix
sigma
sigma
sigma
tanh
endmatrix
right W ht1 xt
ct ft odot ct1 it odot jt
ht ot odot tanhct
We treated last hidden LSTM output him as the clause embedding and concatenated that with the corresponding meta information vector ei The combined vector was linearly transformed and then fed into a softmax function Next our GlobalContext RNN investigated the influence of clauselevel context in detecting social no...
<s>[INST] Open-Vocabulary Semantic Parsing with both Distributional Statistics and Formal Knowledge [/INST] Semantic parsing is the task of mapping a phrase in natural language onto a formal query in some fixed schema which can then be executed against a knowledge base KB BIBREF0 BIBREF1 For example the phrase Who is...
theta rT phi e1 e2 The probability of a predicate instance is the sigmoided inner product of the corresponding predicate and entity embeddings Predicates with nearby embeddings will have similar distributions over the entities in their denotation The parameters theta and phi are learned using a query ranking objec...
pce sigma theta cT phi e omega cT psi ce
pre1 e2 sigma theta rT phi e1 e2 omega rT psi re1 e2
In these equations theta and phi are learned predicate and entity embeddings as described in Section Subgraph feature extraction The second term in the sum represents our new features and their learned weights psi ce and psi re1 e2 are SFE feature vectors for each entity and entity pair a different set of features...
textsc Palladio Here the textit NN predicate represents a generic noun modifier relation however this relation is too vague for the predicate model to accurately learn its denotation A similar problem occurs with prepositions and possessives eg it is similarly hard to learn the denotation of the predicate textit of O...
<s>[INST] Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling [/INST] Stateoftheart models for natural language processing NLP tasks like translation question answering and parsing include components intended to extract representations for the meaning and contents of each ...
<s>[INST] A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network [/INST] Largescale knowledge bases KBs such as YAGO BIBREF0 Freebase BIBREF1 and DBpedia BIBREF2 are usually databases of triples representing the relationships between entities in the form of fact head entity relati...
beginarrayl
1textfor hrtin mathcal G
1textfor hrtin mathcal Gprime
endarray right Eq
mathcal L sum beginarraychrt in lbrace mathcal G cup mathcal Gprime rbrace endarray log left1 exp leftlhrt cdot flefthrtrightrightright nonumber
fraclambda 2Vert wVert 22 nonumber
here mathcal Gprime is a collection of invalid triples generated by corrupting valid triples in mathcal G We evaluate ConvKB on two benchmark datasets WN18RR BIBREF30 and FB15k237 BIBREF31 WN18RR and FB15k237 are correspondingly subsets of two common datasets WN18 and FB15k BIBREF13 As noted by BIBREF31 WN18 and...