Matches in SemOpenAlex for { <https://semopenalex.org/work/W2984210373> ?p ?o ?g. }
- W2984210373 abstract "Supervised training of neural models to duplicate question detection in community Question Answering (cQA) requires large amounts of labeled question pairs, which are costly to obtain. To minimize this cost, recent works thus often used alternative methods, e.g., adversarial domain adaptation. In this work, we propose two novel methods: (1) the automatic generation of duplicate questions, and (2) weak supervision using the title and body of a question. We show that both can achieve improved performances even though they do not require any labeled data. We provide comprehensive comparisons of popular training strategies, which provides important insights on how to best train models in different scenarios. We show that our proposed approaches are more effective in many cases because they can utilize larger amounts of unlabeled data from cQA forums. Finally, we also show that our proposed approach for weak supervision with question title and body information is also an effective method to train cQA answer selection models without direct answer supervision." @default.
- W2984210373 created "2019-11-22" @default.
- W2984210373 creator A5014688346 @default.
- W2984210373 creator A5027450194 @default.
- W2984210373 creator A5054918343 @default.
- W2984210373 date "2019-11-13" @default.
- W2984210373 modified "2023-10-01" @default.
- W2984210373 title "Neural Duplicate Question Detection without Labeled Training Data" @default.
- W2984210373 cites W1970875273 @default.
- W2984210373 cites W1994842363 @default.
- W2984210373 cites W2102394389 @default.
- W2984210373 cites W2120284981 @default.
- W2984210373 cites W2147308966 @default.
- W2984210373 cites W2162355876 @default.
- W2984210373 cites W2250175451 @default.
- W2984210373 cites W2467173223 @default.
- W2984210373 cites W2517782820 @default.
- W2984210373 cites W2537306733 @default.
- W2984210373 cites W2583962582 @default.
- W2984210373 cites W2606974598 @default.
- W2984210373 cites W2739599645 @default.
- W2984210373 cites W2740106139 @default.
- W2984210373 cites W2757978590 @default.
- W2984210373 cites W2787535324 @default.
- W2984210373 cites W2793348910 @default.
- W2984210373 cites W2793381978 @default.
- W2984210373 cites W2799014768 @default.
- W2984210373 cites W2809324505 @default.
- W2984210373 cites W2823604564 @default.
- W2984210373 cites W2890166583 @default.
- W2984210373 cites W2892202790 @default.
- W2984210373 cites W2896457183 @default.
- W2984210373 cites W2900338099 @default.
- W2984210373 cites W2913337508 @default.
- W2984210373 cites W2915240437 @default.
- W2984210373 cites W2962717047 @default.
- W2984210373 cites W2962965405 @default.
- W2984210373 cites W2962970841 @default.
- W2984210373 cites W2962977247 @default.
- W2984210373 cites W2963001778 @default.
- W2984210373 cites W2963142369 @default.
- W2984210373 cites W2963403868 @default.
- W2984210373 cites W2964245140 @default.
- W2984210373 cites W2965373594 @default.
- W2984210373 hasPublicationYear "2019" @default.
- W2984210373 type Work @default.
- W2984210373 sameAs 2984210373 @default.
- W2984210373 citedByCount "0" @default.
- W2984210373 crossrefType "posted-content" @default.
- W2984210373 hasAuthorship W2984210373A5014688346 @default.
- W2984210373 hasAuthorship W2984210373A5027450194 @default.
- W2984210373 hasAuthorship W2984210373A5054918343 @default.
- W2984210373 hasConcept C119857082 @default.
- W2984210373 hasConcept C120665830 @default.
- W2984210373 hasConcept C121332964 @default.
- W2984210373 hasConcept C124101348 @default.
- W2984210373 hasConcept C134306372 @default.
- W2984210373 hasConcept C139807058 @default.
- W2984210373 hasConcept C153294291 @default.
- W2984210373 hasConcept C154945302 @default.
- W2984210373 hasConcept C2776145971 @default.
- W2984210373 hasConcept C2776434776 @default.
- W2984210373 hasConcept C2777211547 @default.
- W2984210373 hasConcept C2984842247 @default.
- W2984210373 hasConcept C33923547 @default.
- W2984210373 hasConcept C36503486 @default.
- W2984210373 hasConcept C37736160 @default.
- W2984210373 hasConcept C41008148 @default.
- W2984210373 hasConcept C44291984 @default.
- W2984210373 hasConcept C50644808 @default.
- W2984210373 hasConcept C51632099 @default.
- W2984210373 hasConcept C81917197 @default.
- W2984210373 hasConcept C95623464 @default.
- W2984210373 hasConceptScore W2984210373C119857082 @default.
- W2984210373 hasConceptScore W2984210373C120665830 @default.
- W2984210373 hasConceptScore W2984210373C121332964 @default.
- W2984210373 hasConceptScore W2984210373C124101348 @default.
- W2984210373 hasConceptScore W2984210373C134306372 @default.
- W2984210373 hasConceptScore W2984210373C139807058 @default.
- W2984210373 hasConceptScore W2984210373C153294291 @default.
- W2984210373 hasConceptScore W2984210373C154945302 @default.
- W2984210373 hasConceptScore W2984210373C2776145971 @default.
- W2984210373 hasConceptScore W2984210373C2776434776 @default.
- W2984210373 hasConceptScore W2984210373C2777211547 @default.
- W2984210373 hasConceptScore W2984210373C2984842247 @default.
- W2984210373 hasConceptScore W2984210373C33923547 @default.
- W2984210373 hasConceptScore W2984210373C36503486 @default.
- W2984210373 hasConceptScore W2984210373C37736160 @default.
- W2984210373 hasConceptScore W2984210373C41008148 @default.
- W2984210373 hasConceptScore W2984210373C44291984 @default.
- W2984210373 hasConceptScore W2984210373C50644808 @default.
- W2984210373 hasConceptScore W2984210373C51632099 @default.
- W2984210373 hasConceptScore W2984210373C81917197 @default.
- W2984210373 hasConceptScore W2984210373C95623464 @default.
- W2984210373 hasLocation W29842103731 @default.
- W2984210373 hasOpenAccess W2984210373 @default.
- W2984210373 hasPrimaryLocation W29842103731 @default.
- W2984210373 hasRelatedWork W2053653724 @default.
- W2984210373 hasRelatedWork W2295615372 @default.
- W2984210373 hasRelatedWork W2556914027 @default.