Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
Open accessAbstract
While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses.Unlike past work that has focused on diversifying the output of the decoder at word-level to alleviate this problem, we present a novel framework based on conditional variational autoencoders that captures the discourse-level diversity in the encoder.Our model uses latent variables to learn a distribution over potential conversational intents and generates diverse responses using only greedy decoders.We have further developed a novel variant that is integrated with linguistic prior knowledge for better performance.Finally, the training procedure is improved by introducing a bag-of-word loss.Our proposed models have been validated to generate significantly more diverse responses than baseline approaches and exhibit competence in discourse-level decision-making.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
VAEs are inherently probabilistic, making them well-suited for tasks that require uncertainty quantification.
“VAEs are inherently probabilistic, making them well-suited for tasks that require uncertainty quantification.”
From A machine learning model that outperforms conventional global subseasonal forecast models (2024) · cites this paper as [87]
In greedy search methodologies, the subsequent token selection consistently prioritizes the one with the greatest probability.
“In greedy search methodologies (Zhao et al. 2017; Xu et al. 2017), the subsequent token selection consistently prioritizes the one with the greatest probability.”
From Large language models (LLMs): survey, technical frameworks, and future challenges (2024) · cites this paper as Zhao et al. 2017
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344 · see citing works
A Systematic Comparison of Smoothing Techniques for Sentence-Level BLEU
Chen, B., & Cherry, C. (2014) · Proceedings of the Ninth Workshop on Statistical Machine Translation · doi:10.3115/v1/w14-3346 · Cited by 191 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
An Introduction to Variational Autoencoders
Kingma, D. P., & Welling, M. (2019) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000056 · Cited by 2,609 · see citing works
Towards a Human-like Open-Domain Chatbot
Adiwardana, D., Luong, M.-T., So, D. R., Hall, J., Fiedel, N., Thoppilan, R., Yang, Z., Kulshreshtha, A., Nemade, G., Lu, Y., et al. (2020) · arXiv · doi:10.48550/arxiv.2001.09977 · Cited by 614 · see citing works
Large language models (LLMs): survey, technical frameworks, and future challenges
Kumar, P. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10888-y · Cited by 395 · see citing works
Challenges in building intelligent open-domain dialog systems
Huang, M., Zhu, X., & Gao, J. (2020) · ACM Transactions on Information Systems · doi:10.1145/3383123 · Cited by 288 · see citing works
USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation
Mehri, S., & Eskenazi, M. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.64 · Cited by 149 · see citing works
Mulla, N., & Gharpure, P. (2023) · Progress in Artificial Intelligence · doi:10.1007/s13748-023-00295-9 · Cited by 132 · see citing works
A machine learning model that outperforms conventional global subseasonal forecast models
Chen, L., Zhong, X., Li, H., Wu, J., Lu, B., Chen, D., Xie, S.-P., Wu, L., Chao, Q., Lin, C., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-50714-1 · Cited by 105 · see citing works
Teaching Machines to Ask Questions
Yao, K., Zhang, L., Luo, T., Tao, L., & Wu, Y. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/632 · Cited by 44 · see citing works
Learning towards conversational AI: A survey
Fu, T., Gao, S., Zhao, X., Wen, J.-R., & Yan, R. (2022) · AI Open · doi:10.1016/j.aiopen.2022.02.001 · Cited by 46 · see citing works
“Mathematical word problem generation from commonsense knowledge graph and equations,”
Liu, T., Fang, Q., Ding, W., Li, H., Wu, Z., & Liu, Z. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.348 · Cited by 29 · see citing works
On the Generation of Medical Question-Answer Pairs
Shen, S., Li, Y., Du, N., Wu, X., Xie, Y., Ge, S., Yang, T., Wang, K., Liang, X., & Fan, W. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6410 · Cited by 25 · see citing works
AutoPal: Autonomous Adaptation to Users for Personal AI Companionship
Cheng, Y., Liu, W., Xu, K., Hou, W., Ouyang, Y., Leong, C. T., Li, W., Wu, X., & Zheng, Y. (2024) · arXiv · doi:10.48550/arxiv.2406.13960 · Cited by 2 · see citing works
- Authors
- Zhao, T., Zhao, R., & Eskenazi, M.
- Affiliations
- Carnegie Mellon University (US)
- Corresponding author
- Zhao, Tiancheng
- Zhao, Ran
- Venue
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2017
- Pages
- 654-664
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W2962717182
- Cited by
- 736
- References
- 3
- Citations by year
- 2026: 6 · 2025: 20 · 2024: 35 · 2023: 78 · 2022: 96 · 2021: 120 · 2020: 171 · 2019: 145 · 2018: 58 · 2017: 7
- FWCI
- 47.52
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1512973)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Keywords
- dialogue response generation, conditional variational autoencoder, latent variables, open-domain conversation, encoder-decoder architecture
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
