Matches in SemOpenAlex for { <https://semopenalex.org/work/W3173647480> ?p ?o ?g. }
- W3173647480 endingPage "14419" @default.
- W3173647480 startingPage "14411" @default.
- W3173647480 abstract "Sentence semantic matching is one of the fundamental tasks in natural language processing, which requires an agent to determine the semantic relation among input sentences. Recently, deep neural networks have achieved impressive performance in this area, especially BERT. Despite the effectiveness of these models, most of them treat output labels as meaningless one-hot vectors, underestimating the semantic information and guidance of relations that these labels reveal, especially for tasks with a small number of labels. To address this problem, we propose a Relation of Relation Learning Network (R2-Net) for sentence semantic matching. Specifically, we first employ BERT to encode the input sentences from a global perspective. Then a CNN-based encoder is designed to capture keywords and phrase information from a local perspective. To fully leverage labels for better relation information extraction, we introduce a self-supervised relation of relation classification task for guiding R2-Net to consider more about labels. Meanwhile, a triplet loss is employed to distinguish the intra-class and inter-class relations in a finer granularity. Empirical experiments on two sentence semantic matching tasks demonstrate the superiority of our proposed model. As a byproduct, we have released the codes to facilitate other researches." @default.
- W3173647480 created "2021-07-05" @default.
- W3173647480 creator A5016038041 @default.
- W3173647480 creator A5028764108 @default.
- W3173647480 creator A5033706423 @default.
- W3173647480 creator A5036726873 @default.
- W3173647480 creator A5047524241 @default.
- W3173647480 creator A5048237545 @default.
- W3173647480 date "2021-05-18" @default.
- W3173647480 modified "2023-10-12" @default.
- W3173647480 title "Making the Relation Matters: Relation of Relation Learning Network for Sentence Semantic Matching" @default.
- W3173647480 cites W131533222 @default.
- W3173647480 cites W1516501661 @default.
- W3173647480 cites W1840435438 @default.
- W3173647480 cites W1973435495 @default.
- W3173647480 cites W2185175083 @default.
- W3173647480 cites W2251385083 @default.
- W3173647480 cites W2251427843 @default.
- W3173647480 cites W2251869843 @default.
- W3173647480 cites W2280395961 @default.
- W3173647480 cites W2413794162 @default.
- W3173647480 cites W2547185913 @default.
- W3173647480 cites W2593833795 @default.
- W3173647480 cites W2756386045 @default.
- W3173647480 cites W2773734397 @default.
- W3173647480 cites W2782363479 @default.
- W3173647480 cites W2788496822 @default.
- W3173647480 cites W2884517879 @default.
- W3173647480 cites W2888087917 @default.
- W3173647480 cites W2888481121 @default.
- W3173647480 cites W2890894339 @default.
- W3173647480 cites W2904664992 @default.
- W3173647480 cites W2906958571 @default.
- W3173647480 cites W2953874899 @default.
- W3173647480 cites W2962765866 @default.
- W3173647480 cites W2962784628 @default.
- W3173647480 cites W2962883855 @default.
- W3173647480 cites W2963241825 @default.
- W3173647480 cites W2963341956 @default.
- W3173647480 cites W2963403868 @default.
- W3173647480 cites W2963912736 @default.
- W3173647480 cites W2964072386 @default.
- W3173647480 cites W2964189376 @default.
- W3173647480 cites W2964308564 @default.
- W3173647480 cites W3099206234 @default.
- W3173647480 cites W3099884890 @default.
- W3173647480 cites W68733909 @default.
- W3173647480 doi "https://doi.org/10.1609/aaai.v35i16.17694" @default.
- W3173647480 hasPublicationYear "2021" @default.
- W3173647480 type Work @default.
- W3173647480 sameAs 3173647480 @default.
- W3173647480 citedByCount "12" @default.
- W3173647480 countsByYear W31736474802021 @default.
- W3173647480 countsByYear W31736474802022 @default.
- W3173647480 countsByYear W31736474802023 @default.
- W3173647480 crossrefType "journal-article" @default.
- W3173647480 hasAuthorship W3173647480A5016038041 @default.
- W3173647480 hasAuthorship W3173647480A5028764108 @default.
- W3173647480 hasAuthorship W3173647480A5033706423 @default.
- W3173647480 hasAuthorship W3173647480A5036726873 @default.
- W3173647480 hasAuthorship W3173647480A5047524241 @default.
- W3173647480 hasAuthorship W3173647480A5048237545 @default.
- W3173647480 hasBestOaLocation W31736474801 @default.
- W3173647480 hasConcept C105795698 @default.
- W3173647480 hasConcept C111919701 @default.
- W3173647480 hasConcept C118505674 @default.
- W3173647480 hasConcept C124101348 @default.
- W3173647480 hasConcept C153083717 @default.
- W3173647480 hasConcept C153604712 @default.
- W3173647480 hasConcept C154945302 @default.
- W3173647480 hasConcept C165064840 @default.
- W3173647480 hasConcept C169760540 @default.
- W3173647480 hasConcept C169900460 @default.
- W3173647480 hasConcept C195807954 @default.
- W3173647480 hasConcept C204321447 @default.
- W3173647480 hasConcept C25343380 @default.
- W3173647480 hasConcept C2776224158 @default.
- W3173647480 hasConcept C2777530160 @default.
- W3173647480 hasConcept C2988080768 @default.
- W3173647480 hasConcept C33923547 @default.
- W3173647480 hasConcept C41008148 @default.
- W3173647480 hasConcept C86803240 @default.
- W3173647480 hasConceptScore W3173647480C105795698 @default.
- W3173647480 hasConceptScore W3173647480C111919701 @default.
- W3173647480 hasConceptScore W3173647480C118505674 @default.
- W3173647480 hasConceptScore W3173647480C124101348 @default.
- W3173647480 hasConceptScore W3173647480C153083717 @default.
- W3173647480 hasConceptScore W3173647480C153604712 @default.
- W3173647480 hasConceptScore W3173647480C154945302 @default.
- W3173647480 hasConceptScore W3173647480C165064840 @default.
- W3173647480 hasConceptScore W3173647480C169760540 @default.
- W3173647480 hasConceptScore W3173647480C169900460 @default.
- W3173647480 hasConceptScore W3173647480C195807954 @default.
- W3173647480 hasConceptScore W3173647480C204321447 @default.
- W3173647480 hasConceptScore W3173647480C25343380 @default.
- W3173647480 hasConceptScore W3173647480C2776224158 @default.
- W3173647480 hasConceptScore W3173647480C2777530160 @default.
- W3173647480 hasConceptScore W3173647480C2988080768 @default.