Matches in SemOpenAlex for { <https://semopenalex.org/work/W2788343755> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2788343755 abstract "The recurrent neural networks (RNNs) have shown good performance for sentence similarity modeling in recent years. Most RNNs focus on modeling the hidden states based on the current sentence, while the context information from the other sentence is not well investigated during the hidden state generation. In this paper, we propose a context-aligned RNN (CA-RNN) model, which incorporates the contextual information of the aligned words in a sentence pair for the inner hidden state generation. Specifically, we first perform word alignment detection to identify the aligned words in the two sentences. Then, we present a context alignment gating mechanism and embed it into our model to automatically absorb the aligned words' context for the hidden state update. Experiments on three benchmark datasets, namely TREC-QA and WikiQA for answer selection and MSRP for paraphrase identification, show the great advantages of our proposed model. In particular, we achieve the new state-of-the-art performance on TREC-QA and WikiQA. Furthermore, our model is comparable to if not better than the recent neural network based approaches on MSRP." @default.
- W2788343755 created "2018-03-06" @default.
- W2788343755 creator A5010540039 @default.
- W2788343755 creator A5018749138 @default.
- W2788343755 creator A5028293439 @default.
- W2788343755 creator A5030368654 @default.
- W2788343755 date "2018-04-25" @default.
- W2788343755 modified "2023-10-15" @default.
- W2788343755 title "CA-RNN: Using Context-Aligned Recurrent Neural Networks for Modeling Sentence Similarity" @default.
- W2788343755 cites W1980776243 @default.
- W2788343755 cites W2739983396 @default.
- W2788343755 cites W2964308564 @default.
- W2788343755 doi "https://doi.org/10.1609/aaai.v32i1.11273" @default.
- W2788343755 hasPublicationYear "2018" @default.
- W2788343755 type Work @default.
- W2788343755 sameAs 2788343755 @default.
- W2788343755 citedByCount "25" @default.
- W2788343755 countsByYear W27883437552018 @default.
- W2788343755 countsByYear W27883437552019 @default.
- W2788343755 countsByYear W27883437552020 @default.
- W2788343755 countsByYear W27883437552021 @default.
- W2788343755 countsByYear W27883437552022 @default.
- W2788343755 countsByYear W27883437552023 @default.
- W2788343755 crossrefType "journal-article" @default.
- W2788343755 hasAuthorship W2788343755A5010540039 @default.
- W2788343755 hasAuthorship W2788343755A5018749138 @default.
- W2788343755 hasAuthorship W2788343755A5028293439 @default.
- W2788343755 hasAuthorship W2788343755A5030368654 @default.
- W2788343755 hasBestOaLocation W27883437551 @default.
- W2788343755 hasConcept C103278499 @default.
- W2788343755 hasConcept C115961682 @default.
- W2788343755 hasConcept C13280743 @default.
- W2788343755 hasConcept C137293760 @default.
- W2788343755 hasConcept C138885662 @default.
- W2788343755 hasConcept C147168706 @default.
- W2788343755 hasConcept C151730666 @default.
- W2788343755 hasConcept C154945302 @default.
- W2788343755 hasConcept C185798385 @default.
- W2788343755 hasConcept C204321447 @default.
- W2788343755 hasConcept C205649164 @default.
- W2788343755 hasConcept C2777530160 @default.
- W2788343755 hasConcept C2779343474 @default.
- W2788343755 hasConcept C2780922921 @default.
- W2788343755 hasConcept C28490314 @default.
- W2788343755 hasConcept C41008148 @default.
- W2788343755 hasConcept C41895202 @default.
- W2788343755 hasConcept C50644808 @default.
- W2788343755 hasConcept C86803240 @default.
- W2788343755 hasConcept C90805587 @default.
- W2788343755 hasConceptScore W2788343755C103278499 @default.
- W2788343755 hasConceptScore W2788343755C115961682 @default.
- W2788343755 hasConceptScore W2788343755C13280743 @default.
- W2788343755 hasConceptScore W2788343755C137293760 @default.
- W2788343755 hasConceptScore W2788343755C138885662 @default.
- W2788343755 hasConceptScore W2788343755C147168706 @default.
- W2788343755 hasConceptScore W2788343755C151730666 @default.
- W2788343755 hasConceptScore W2788343755C154945302 @default.
- W2788343755 hasConceptScore W2788343755C185798385 @default.
- W2788343755 hasConceptScore W2788343755C204321447 @default.
- W2788343755 hasConceptScore W2788343755C205649164 @default.
- W2788343755 hasConceptScore W2788343755C2777530160 @default.
- W2788343755 hasConceptScore W2788343755C2779343474 @default.
- W2788343755 hasConceptScore W2788343755C2780922921 @default.
- W2788343755 hasConceptScore W2788343755C28490314 @default.
- W2788343755 hasConceptScore W2788343755C41008148 @default.
- W2788343755 hasConceptScore W2788343755C41895202 @default.
- W2788343755 hasConceptScore W2788343755C50644808 @default.
- W2788343755 hasConceptScore W2788343755C86803240 @default.
- W2788343755 hasConceptScore W2788343755C90805587 @default.
- W2788343755 hasIssue "1" @default.
- W2788343755 hasLocation W27883437551 @default.
- W2788343755 hasOpenAccess W2788343755 @default.
- W2788343755 hasPrimaryLocation W27883437551 @default.
- W2788343755 hasRelatedWork W191017350 @default.
- W2788343755 hasRelatedWork W2018298289 @default.
- W2788343755 hasRelatedWork W2160451571 @default.
- W2788343755 hasRelatedWork W2251069562 @default.
- W2788343755 hasRelatedWork W2782520308 @default.
- W2788343755 hasRelatedWork W2944691285 @default.
- W2788343755 hasRelatedWork W3137243147 @default.
- W2788343755 hasRelatedWork W3175194702 @default.
- W2788343755 hasRelatedWork W4206666510 @default.
- W2788343755 hasRelatedWork W4321512656 @default.
- W2788343755 hasVolume "32" @default.
- W2788343755 isParatext "false" @default.
- W2788343755 isRetracted "false" @default.
- W2788343755 magId "2788343755" @default.
- W2788343755 workType "article" @default.