Improving contextual coherence in variational personalized and empathetic dialogue agents
In recent years, latent variable models, such as the Conditional Variational Auto Encoder (CVAE), have been applied to both personalized and empathetic dialogue generation. Prior work have largely focused on generating diverse dialogue responses that exhibit persona consistency and empathy. However,...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/159792 |
| _version_ | 1824456021542699008 |
|---|---|
| author | Lee, Jing Yang Lee, Kong Aik Gan, Woon Seng |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Lee, Jing Yang Lee, Kong Aik Gan, Woon Seng |
| author_sort | Lee, Jing Yang |
| collection | NTU |
| description | In recent years, latent variable models, such as the Conditional Variational Auto Encoder (CVAE), have been applied to both personalized and empathetic dialogue generation. Prior work have largely focused on generating diverse dialogue responses that exhibit persona consistency and empathy. However, when it comes to the contextual coherence of the generated responses, there is still room for improvement. Hence, to improve the contextual coherence, we propose a novel Uncertainty Aware CVAE (UA-CVAE) framework. The UA-CVAE framework involves approximating and incorporating the aleatoric uncertainty during response generation. We apply our framework to both personalized and empathetic dialogue generation. Empirical results show that our framework significantly improves the contextual coherence of the generated response. Additionally, we introduce a novel automatic metric for measuring contextual coherence, which was found to correlate positively with human judgement. |
| first_indexed | 2025-02-19T03:47:29Z |
| format | Conference Paper |
| id | ntu-10356/159792 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:47:29Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1597922022-07-05T08:52:27Z Improving contextual coherence in variational personalized and empathetic dialogue agents Lee, Jing Yang Lee, Kong Aik Gan, Woon Seng School of Electrical and Electronic Engineering 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2022) Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Dialogue Generation Latent Variables In recent years, latent variable models, such as the Conditional Variational Auto Encoder (CVAE), have been applied to both personalized and empathetic dialogue generation. Prior work have largely focused on generating diverse dialogue responses that exhibit persona consistency and empathy. However, when it comes to the contextual coherence of the generated responses, there is still room for improvement. Hence, to improve the contextual coherence, we propose a novel Uncertainty Aware CVAE (UA-CVAE) framework. The UA-CVAE framework involves approximating and incorporating the aleatoric uncertainty during response generation. We apply our framework to both personalized and empathetic dialogue generation. Empirical results show that our framework significantly improves the contextual coherence of the generated response. Additionally, we introduce a novel automatic metric for measuring contextual coherence, which was found to correlate positively with human judgement. Submitted/Accepted version 2022-07-05T08:52:27Z 2022-07-05T08:52:27Z 2022 Conference Paper Lee, J. Y., Lee, K. A. & Gan, W. S. (2022). Improving contextual coherence in variational personalized and empathetic dialogue agents. 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2022), 7052-7056. https://dx.doi.org/10.1109/ICASSP43922.2022.9747458 978-1-6654-0540-9 https://hdl.handle.net/10356/159792 10.1109/ICASSP43922.2022.9747458 7052 7056 en © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/ICASSP43922.2022.9747458. application/pdf |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Dialogue Generation Latent Variables Lee, Jing Yang Lee, Kong Aik Gan, Woon Seng Improving contextual coherence in variational personalized and empathetic dialogue agents |
| title | Improving contextual coherence in variational personalized and empathetic dialogue agents |
| title_full | Improving contextual coherence in variational personalized and empathetic dialogue agents |
| title_fullStr | Improving contextual coherence in variational personalized and empathetic dialogue agents |
| title_full_unstemmed | Improving contextual coherence in variational personalized and empathetic dialogue agents |
| title_short | Improving contextual coherence in variational personalized and empathetic dialogue agents |
| title_sort | improving contextual coherence in variational personalized and empathetic dialogue agents |
| topic | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Dialogue Generation Latent Variables |
| url | https://hdl.handle.net/10356/159792 |
| work_keys_str_mv | AT leejingyang improvingcontextualcoherenceinvariationalpersonalizedandempatheticdialogueagents AT leekongaik improvingcontextualcoherenceinvariationalpersonalizedandempatheticdialogueagents AT ganwoonseng improvingcontextualcoherenceinvariationalpersonalizedandempatheticdialogueagents |