A Seq2Seq based model for generating diverse sentiment dialogues

HongSong Chen; JunXiu An; QuanHui Tao

doi:10.1117/12.2667315

28 March 2023 A Seq2Seq based model for generating diverse sentiment dialogues

HongSong Chen, JunXiu An, QuanHui Tao

Proceedings Volume 12566, Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022); 125663L (2023) https://doi.org/10.1117/12.2667315
Event: Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 2022, Chongqing, China

Abstract

To address the problems of poor attention to the richness of dialogue content and emotional responses in human-computer interaction, it is valuable to study how to make the machine responses diverse and emotional. A Multi-Style Emotional Dialogue Generation (MEDG) model is proposed, which uses Sequence to Sequence (Seq2Seq) as the text generation model. Firstly, the implicit function in the Seq2Seq encoder is mapped using sentiment sentence vector mapping and introducing an attention mechanism, which increases the sentiment constraint of the model in the generation process. Secondly, penalty factors and output vectors are introduced in the decoder to make the decoded results have diversity. Finally, experimental tests were conducted on an open network dataset, and the results showed that the MEDG model had better scores.

Citation Download Citation

HongSong Chen, JunXiu An, and QuanHui Tao "A Seq2Seq based model for generating diverse sentiment dialogues", Proc. SPIE 12566, Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 125663L (28 March 2023); https://doi.org/10.1117/12.2667315

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available