Matches in SemOpenAlex for { <https://semopenalex.org/work/W2905285669> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2905285669 abstract "In recent years, deep neural networks have achieved significant success in relation classification and many other natural language processing tasks. However, existing neural networks for relation classification heavily rely on the quality of labelled data and tend to be overconfident about the noise in input signals. They may be limited in robustness and generalization. In this paper, we apply adversarial training to the relation classification by adding perturbations to the input vectors in bidirectional long short-term memory neural networks rather than to the original input itself. Besides, we propose an attention based gate module, which can not only discern the important information when learning the sentence representations but also adaptively concatenate sentence level and lexical level features. Experiments on the SemEval-2010 Task 8 benchmark dataset show that our model significantly outperforms other state-of-the-art models." @default.
- W2905285669 created "2018-12-22" @default.
- W2905285669 creator A5045570568 @default.
- W2905285669 creator A5052757090 @default.
- W2905285669 creator A5071321132 @default.
- W2905285669 creator A5079010450 @default.
- W2905285669 date "2018-12-07" @default.
- W2905285669 modified "2023-09-23" @default.
- W2905285669 title "Adversarial Training for Relation Classification with Attention Based Gate Mechanism" @default.
- W2905285669 cites W2053238041 @default.
- W2905285669 cites W2064675550 @default.
- W2905285669 cites W2099779943 @default.
- W2905285669 cites W2110485445 @default.
- W2905285669 cites W2138627627 @default.
- W2905285669 cites W2148721079 @default.
- W2905285669 cites W2165935464 @default.
- W2905285669 cites W2250539671 @default.
- W2905285669 cites W2283260092 @default.
- W2905285669 cites W2517194566 @default.
- W2905285669 cites W2760600531 @default.
- W2905285669 cites W2963171262 @default.
- W2905285669 cites W2964217331 @default.
- W2905285669 doi "https://doi.org/10.1007/978-981-13-3146-6_8" @default.
- W2905285669 hasPublicationYear "2018" @default.
- W2905285669 type Work @default.
- W2905285669 sameAs 2905285669 @default.
- W2905285669 citedByCount "0" @default.
- W2905285669 crossrefType "book-chapter" @default.
- W2905285669 hasAuthorship W2905285669A5045570568 @default.
- W2905285669 hasAuthorship W2905285669A5052757090 @default.
- W2905285669 hasAuthorship W2905285669A5071321132 @default.
- W2905285669 hasAuthorship W2905285669A5079010450 @default.
- W2905285669 hasConcept C104317684 @default.
- W2905285669 hasConcept C119857082 @default.
- W2905285669 hasConcept C124101348 @default.
- W2905285669 hasConcept C13280743 @default.
- W2905285669 hasConcept C134306372 @default.
- W2905285669 hasConcept C154945302 @default.
- W2905285669 hasConcept C162324750 @default.
- W2905285669 hasConcept C177148314 @default.
- W2905285669 hasConcept C185592680 @default.
- W2905285669 hasConcept C185798385 @default.
- W2905285669 hasConcept C187736073 @default.
- W2905285669 hasConcept C204321447 @default.
- W2905285669 hasConcept C205649164 @default.
- W2905285669 hasConcept C25343380 @default.
- W2905285669 hasConcept C2777530160 @default.
- W2905285669 hasConcept C2780451532 @default.
- W2905285669 hasConcept C33923547 @default.
- W2905285669 hasConcept C37736160 @default.
- W2905285669 hasConcept C41008148 @default.
- W2905285669 hasConcept C44572571 @default.
- W2905285669 hasConcept C50644808 @default.
- W2905285669 hasConcept C55493867 @default.
- W2905285669 hasConcept C63479239 @default.
- W2905285669 hasConceptScore W2905285669C104317684 @default.
- W2905285669 hasConceptScore W2905285669C119857082 @default.
- W2905285669 hasConceptScore W2905285669C124101348 @default.
- W2905285669 hasConceptScore W2905285669C13280743 @default.
- W2905285669 hasConceptScore W2905285669C134306372 @default.
- W2905285669 hasConceptScore W2905285669C154945302 @default.
- W2905285669 hasConceptScore W2905285669C162324750 @default.
- W2905285669 hasConceptScore W2905285669C177148314 @default.
- W2905285669 hasConceptScore W2905285669C185592680 @default.
- W2905285669 hasConceptScore W2905285669C185798385 @default.
- W2905285669 hasConceptScore W2905285669C187736073 @default.
- W2905285669 hasConceptScore W2905285669C204321447 @default.
- W2905285669 hasConceptScore W2905285669C205649164 @default.
- W2905285669 hasConceptScore W2905285669C25343380 @default.
- W2905285669 hasConceptScore W2905285669C2777530160 @default.
- W2905285669 hasConceptScore W2905285669C2780451532 @default.
- W2905285669 hasConceptScore W2905285669C33923547 @default.
- W2905285669 hasConceptScore W2905285669C37736160 @default.
- W2905285669 hasConceptScore W2905285669C41008148 @default.
- W2905285669 hasConceptScore W2905285669C44572571 @default.
- W2905285669 hasConceptScore W2905285669C50644808 @default.
- W2905285669 hasConceptScore W2905285669C55493867 @default.
- W2905285669 hasConceptScore W2905285669C63479239 @default.
- W2905285669 hasLocation W29052856691 @default.
- W2905285669 hasOpenAccess W2905285669 @default.
- W2905285669 hasPrimaryLocation W29052856691 @default.
- W2905285669 hasRelatedWork W2104740481 @default.
- W2905285669 hasRelatedWork W2254842198 @default.
- W2905285669 hasRelatedWork W2465978385 @default.
- W2905285669 hasRelatedWork W2472967012 @default.
- W2905285669 hasRelatedWork W2602596682 @default.
- W2905285669 hasRelatedWork W2806213554 @default.
- W2905285669 hasRelatedWork W2806593956 @default.
- W2905285669 hasRelatedWork W2945428946 @default.
- W2905285669 hasRelatedWork W2949737549 @default.
- W2905285669 hasRelatedWork W78638240 @default.
- W2905285669 isParatext "false" @default.
- W2905285669 isRetracted "false" @default.
- W2905285669 magId "2905285669" @default.
- W2905285669 workType "book-chapter" @default.