Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/139252
Full metadata record
DC FieldValueLanguage
dc.contributor.authorZhong, Peixiangen_US
dc.contributor.authorWang, Dien_US
dc.contributor.authorMiao, Chunyanen_US
dc.date.accessioned2020-05-18T06:55:37Z-
dc.date.available2020-05-18T06:55:37Z-
dc.date.issued2018-
dc.identifier.citationZhong, P., Wang, D., & Miao, C. (2018). An affect-rich neural conversational model with biased attention and weighted cross-entropy loss. Proceedings of The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19), 7492-7500.en_US
dc.identifier.urihttps://arxiv.org/abs/1811.07078-
dc.identifier.urihttps://hdl.handle.net/10356/139252-
dc.description.abstractAffect conveys important implicit information in human communication. Having the capability to correctly express affect during human-machine conversations is one of the major milestones in artificial intelligence. In recent years, extensive research on open-domain neural conversational models has been conducted. However, embedding affect into such models is still under explored. In this paper, we propose an endto-end affect-rich open-domain neural conversational model that produces responses not only appropriate in syntax and semantics, but also with rich affect. Our model extends the Seq2Seq model and adopts VAD (Valence, Arousal and Dominance) affective notations to embed each word with affects. In addition, our model considers the effect of negators and intensifiers via a novel affective attention mechanism, which biases attention towards affect-rich words in input sentences. Lastly, we train our model with an affect-incorporated objective function to encourage the generation of affect-rich words in the output responses. Evaluations based on both perplexity and human evaluations show that our model outperforms the state-of-the-art baseline model of comparable size in producing natural and affect-rich responses.en_US
dc.description.sponsorshipNRF (Natl Research Foundation, S’pore)en_US
dc.description.sponsorshipMOH (Min. of Health, S’pore)en_US
dc.language.isoenen_US
dc.rights© 2019 Association for the Advancement of Artificial Intelligence. All rights reserved. This paper was published in The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19) and is made available with permission of Association for the Advancement of Artificial Intelligence.en_US
dc.subjectEngineering::Computer science and engineeringen_US
dc.titleAn affect-rich neural conversational model with biased attention and weighted cross-entropy lossen_US
dc.typeConference Paperen
dc.contributor.schoolSchool of Computer Science and Engineeringen_US
dc.contributor.conferenceThe Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19)en_US
dc.contributor.organizationJoint NTU-UBC Research Centre of Excellence in Active Living for the Elderlyen_US
dc.contributor.organizationAlibaba-NTU Singapore Joint Research Instituteen_US
dc.description.versionAccepted versionen_US
dc.identifier.spage7492en_US
dc.identifier.epage7500en_US
dc.subject.keywordsComputation and Languageen_US
dc.subject.keywordsArtificial Intelligenceen_US
item.grantfulltextopen-
item.fulltextWith Fulltext-
Appears in Collections:SCSE Conference Papers

Page view(s)

100
Updated on Jan 29, 2023

Download(s) 50

35
Updated on Jan 29, 2023

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.