Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100355408> ?p ?o ?g. }
- W3100355408 abstract "Dialogue systems play an increasingly important role in various aspects of our daily life. It is evident from recent research that dialogue systems trained on human conversation data are biased. In particular, they can produce responses that reflect people's gender prejudice. Many debiasing methods have been developed for various NLP tasks, such as word embedding. However, they are not directly applicable to dialogue systems because they are likely to force dialogue models to generate similar responses for different genders. This greatly degrades the diversity of the generated responses and immensely hurts the performance of the dialogue models. In this paper, we propose a novel adversarial learning framework Debiased-Chat to train dialogue models free from gender bias while keeping their performance. Extensive experiments on two real-world conversation datasets show that our framework significantly reduces gender bias in dialogue models while maintaining the response quality. The implementation of the proposed framework is released." @default.
- W3100355408 created "2020-11-23" @default.
- W3100355408 creator A5014957271 @default.
- W3100355408 creator A5040639891 @default.
- W3100355408 creator A5044301848 @default.
- W3100355408 creator A5047904253 @default.
- W3100355408 creator A5064509388 @default.
- W3100355408 creator A5070500491 @default.
- W3100355408 date "2020-01-01" @default.
- W3100355408 modified "2023-10-16" @default.
- W3100355408 title "Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learning" @default.
- W3100355408 cites W2054192854 @default.
- W3100355408 cites W2143017621 @default.
- W3100355408 cites W2157331557 @default.
- W3100355408 cites W2187089797 @default.
- W3100355408 cites W2483215953 @default.
- W3100355408 cites W2510955516 @default.
- W3100355408 cites W2547875792 @default.
- W3100355408 cites W2565378226 @default.
- W3100355408 cites W2581637843 @default.
- W3100355408 cites W2758912220 @default.
- W3100355408 cites W2760062370 @default.
- W3100355408 cites W2962917899 @default.
- W3100355408 cites W2963078909 @default.
- W3100355408 cites W2963206148 @default.
- W3100355408 cites W2963363122 @default.
- W3100355408 cites W2963524705 @default.
- W3100355408 cites W2963526187 @default.
- W3100355408 cites W2963612262 @default.
- W3100355408 cites W2963825865 @default.
- W3100355408 cites W2964119254 @default.
- W3100355408 cites W2964121744 @default.
- W3100355408 cites W2964352131 @default.
- W3100355408 cites W2972766508 @default.
- W3100355408 cites W3013520104 @default.
- W3100355408 cites W3015001695 @default.
- W3100355408 cites W3031668985 @default.
- W3100355408 cites W3103639864 @default.
- W3100355408 cites W3104617516 @default.
- W3100355408 cites W3117655171 @default.
- W3100355408 cites W3181414820 @default.
- W3100355408 doi "https://doi.org/10.18653/v1/2020.emnlp-main.64" @default.
- W3100355408 hasPublicationYear "2020" @default.
- W3100355408 type Work @default.
- W3100355408 sameAs 3100355408 @default.
- W3100355408 citedByCount "34" @default.
- W3100355408 countsByYear W31003554082019 @default.
- W3100355408 countsByYear W31003554082020 @default.
- W3100355408 countsByYear W31003554082021 @default.
- W3100355408 countsByYear W31003554082022 @default.
- W3100355408 countsByYear W31003554082023 @default.
- W3100355408 crossrefType "proceedings-article" @default.
- W3100355408 hasAuthorship W3100355408A5014957271 @default.
- W3100355408 hasAuthorship W3100355408A5040639891 @default.
- W3100355408 hasAuthorship W3100355408A5044301848 @default.
- W3100355408 hasAuthorship W3100355408A5047904253 @default.
- W3100355408 hasAuthorship W3100355408A5064509388 @default.
- W3100355408 hasAuthorship W3100355408A5070500491 @default.
- W3100355408 hasBestOaLocation W31003554081 @default.
- W3100355408 hasConcept C107062074 @default.
- W3100355408 hasConcept C111472728 @default.
- W3100355408 hasConcept C119857082 @default.
- W3100355408 hasConcept C138885662 @default.
- W3100355408 hasConcept C144024400 @default.
- W3100355408 hasConcept C154945302 @default.
- W3100355408 hasConcept C15744967 @default.
- W3100355408 hasConcept C180747234 @default.
- W3100355408 hasConcept C188147891 @default.
- W3100355408 hasConcept C19165224 @default.
- W3100355408 hasConcept C204321447 @default.
- W3100355408 hasConcept C2777200299 @default.
- W3100355408 hasConcept C2777462759 @default.
- W3100355408 hasConcept C2779458634 @default.
- W3100355408 hasConcept C2779530757 @default.
- W3100355408 hasConcept C2781316041 @default.
- W3100355408 hasConcept C2983427547 @default.
- W3100355408 hasConcept C37736160 @default.
- W3100355408 hasConcept C41008148 @default.
- W3100355408 hasConcept C41608201 @default.
- W3100355408 hasConcept C41895202 @default.
- W3100355408 hasConcept C46312422 @default.
- W3100355408 hasConcept C77805123 @default.
- W3100355408 hasConcept C90805587 @default.
- W3100355408 hasConceptScore W3100355408C107062074 @default.
- W3100355408 hasConceptScore W3100355408C111472728 @default.
- W3100355408 hasConceptScore W3100355408C119857082 @default.
- W3100355408 hasConceptScore W3100355408C138885662 @default.
- W3100355408 hasConceptScore W3100355408C144024400 @default.
- W3100355408 hasConceptScore W3100355408C154945302 @default.
- W3100355408 hasConceptScore W3100355408C15744967 @default.
- W3100355408 hasConceptScore W3100355408C180747234 @default.
- W3100355408 hasConceptScore W3100355408C188147891 @default.
- W3100355408 hasConceptScore W3100355408C19165224 @default.
- W3100355408 hasConceptScore W3100355408C204321447 @default.
- W3100355408 hasConceptScore W3100355408C2777200299 @default.
- W3100355408 hasConceptScore W3100355408C2777462759 @default.
- W3100355408 hasConceptScore W3100355408C2779458634 @default.
- W3100355408 hasConceptScore W3100355408C2779530757 @default.
- W3100355408 hasConceptScore W3100355408C2781316041 @default.
- W3100355408 hasConceptScore W3100355408C2983427547 @default.