Beyond Goldfish Memory: Long-Term Open-Domain Conversation

Jing Xu, Arthur Szlam, Jason Weston


Abstract
Despite recent improvements in open-domain dialogue models, state of the art models are trained and evaluated on short conversations with little context. In contrast, the long-term conversation setting has hardly been studied. In this work we collect and release a human-human dataset consisting of multiple chat sessions whereby the speaking partners learn about each other’s interests and discuss the things they have learnt from past sessions. We show how existing models trained on existing datasets perform poorly in this long-term conversation setting in both automatic and human evaluations, and we study long-context models that can perform much better. In particular, we find retrieval-augmented methods and methods with an ability to summarize and recall previous conversations outperform the standard encoder-decoder architectures currently considered state of the art.
Anthology ID:
2022.acl-long.356
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5180–5197
Language:
URL:
https://aclanthology.org/2022.acl-long.356
DOI:
10.18653/v1/2022.acl-long.356
Bibkey:
Cite (ACL):
Jing Xu, Arthur Szlam, and Jason Weston. 2022. Beyond Goldfish Memory: Long-Term Open-Domain Conversation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5180–5197, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Beyond Goldfish Memory: Long-Term Open-Domain Conversation (Xu et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.acl-long.356.pdf
Data
Facebook MSC