Matches in SemOpenAlex for { <https://semopenalex.org/work/W3212781411> ?p ?o ?g. }
- W3212781411 abstract "Natural language generation (NLG) tasks on pro-drop languages are known to suffer from zero pronoun (ZP) problems, and the problems remain challenging due to the scarcity of ZP-annotated NLG corpora. In this case, we propose a highly adaptive two-stage approach to couple context modeling with ZP recovering to mitigate the ZP problem in NLG tasks. Notably, we frame the recovery process in a task-supervised fashion where the ZP representation recovering capability is learned during the NLG task learning process, thus our method does not require NLG corpora annotated with ZPs. For system enhancement, we learn an adversarial bot to adjust our model outputs to alleviate the error propagation caused by mis-recovered ZPs. Experiments on three document-level NLG tasks, i.e., machine translation, question answering, and summarization, show that our approach can improve the performance to a great extent, and the improvement on pronoun translation is very impressive." @default.
- W3212781411 created "2021-11-22" @default.
- W3212781411 creator A5012794465 @default.
- W3212781411 creator A5071953338 @default.
- W3212781411 creator A5080281882 @default.
- W3212781411 date "2021-01-01" @default.
- W3212781411 modified "2023-10-13" @default.
- W3212781411 title "Coupling Context Modeling with Zero Pronoun Recovering for Document-Level Natural Language Generation" @default.
- W3212781411 cites W150892692 @default.
- W3212781411 cites W1525595230 @default.
- W3212781411 cites W1902237438 @default.
- W3212781411 cites W204341599 @default.
- W3212781411 cites W2108188641 @default.
- W3212781411 cites W2150824314 @default.
- W3212781411 cites W2157331557 @default.
- W3212781411 cites W2184135559 @default.
- W3212781411 cites W2250464567 @default.
- W3212781411 cites W2296330515 @default.
- W3212781411 cites W2340762547 @default.
- W3212781411 cites W2582446770 @default.
- W3212781411 cites W2891534142 @default.
- W3212781411 cites W2946581011 @default.
- W3212781411 cites W2949888546 @default.
- W3212781411 cites W2962712961 @default.
- W3212781411 cites W2962943802 @default.
- W3212781411 cites W2962979827 @default.
- W3212781411 cites W2963194310 @default.
- W3212781411 cites W2963212250 @default.
- W3212781411 cites W2963341956 @default.
- W3212781411 cites W2963403868 @default.
- W3212781411 cites W2963406609 @default.
- W3212781411 cites W2963888230 @default.
- W3212781411 cites W2963959336 @default.
- W3212781411 cites W2963970666 @default.
- W3212781411 cites W2964289193 @default.
- W3212781411 cites W2964324871 @default.
- W3212781411 cites W2970419734 @default.
- W3212781411 cites W2971248291 @default.
- W3212781411 cites W2971278086 @default.
- W3212781411 cites W2971287409 @default.
- W3212781411 cites W2999230881 @default.
- W3212781411 cites W3034786666 @default.
- W3212781411 cites W3035446106 @default.
- W3212781411 cites W3035736543 @default.
- W3212781411 cites W3101683892 @default.
- W3212781411 cites W3102685326 @default.
- W3212781411 cites W3105492496 @default.
- W3212781411 cites W80257477 @default.
- W3212781411 doi "https://doi.org/10.18653/v1/2021.emnlp-main.197" @default.
- W3212781411 hasPublicationYear "2021" @default.
- W3212781411 type Work @default.
- W3212781411 sameAs 3212781411 @default.
- W3212781411 citedByCount "1" @default.
- W3212781411 countsByYear W32127814112023 @default.
- W3212781411 crossrefType "proceedings-article" @default.
- W3212781411 hasAuthorship W3212781411A5012794465 @default.
- W3212781411 hasAuthorship W3212781411A5071953338 @default.
- W3212781411 hasAuthorship W3212781411A5080281882 @default.
- W3212781411 hasBestOaLocation W32127814111 @default.
- W3212781411 hasConcept C138885662 @default.
- W3212781411 hasConcept C151730666 @default.
- W3212781411 hasConcept C154945302 @default.
- W3212781411 hasConcept C162324750 @default.
- W3212781411 hasConcept C170858558 @default.
- W3212781411 hasConcept C17744445 @default.
- W3212781411 hasConcept C187736073 @default.
- W3212781411 hasConcept C195324797 @default.
- W3212781411 hasConcept C199539241 @default.
- W3212781411 hasConcept C203005215 @default.
- W3212781411 hasConcept C204321447 @default.
- W3212781411 hasConcept C2776187449 @default.
- W3212781411 hasConcept C2776359362 @default.
- W3212781411 hasConcept C2778551981 @default.
- W3212781411 hasConcept C2779343474 @default.
- W3212781411 hasConcept C2780451532 @default.
- W3212781411 hasConcept C41008148 @default.
- W3212781411 hasConcept C41895202 @default.
- W3212781411 hasConcept C86803240 @default.
- W3212781411 hasConcept C94625758 @default.
- W3212781411 hasConceptScore W3212781411C138885662 @default.
- W3212781411 hasConceptScore W3212781411C151730666 @default.
- W3212781411 hasConceptScore W3212781411C154945302 @default.
- W3212781411 hasConceptScore W3212781411C162324750 @default.
- W3212781411 hasConceptScore W3212781411C170858558 @default.
- W3212781411 hasConceptScore W3212781411C17744445 @default.
- W3212781411 hasConceptScore W3212781411C187736073 @default.
- W3212781411 hasConceptScore W3212781411C195324797 @default.
- W3212781411 hasConceptScore W3212781411C199539241 @default.
- W3212781411 hasConceptScore W3212781411C203005215 @default.
- W3212781411 hasConceptScore W3212781411C204321447 @default.
- W3212781411 hasConceptScore W3212781411C2776187449 @default.
- W3212781411 hasConceptScore W3212781411C2776359362 @default.
- W3212781411 hasConceptScore W3212781411C2778551981 @default.
- W3212781411 hasConceptScore W3212781411C2779343474 @default.
- W3212781411 hasConceptScore W3212781411C2780451532 @default.
- W3212781411 hasConceptScore W3212781411C41008148 @default.
- W3212781411 hasConceptScore W3212781411C41895202 @default.
- W3212781411 hasConceptScore W3212781411C86803240 @default.
- W3212781411 hasConceptScore W3212781411C94625758 @default.
- W3212781411 hasLocation W32127814111 @default.