Pre-training Multi-party Dialogue Models with Latent Discourse Inference

Yiyang Li, Xinting Huang, Wei Bi, Hai Zhao


Abstract
Multi-party dialogues are more difficult for models to understand than one-to-one two-party dialogues, since they involve multiple interlocutors, resulting in interweaving reply-to relations and information flows. To step over these obstacles, an effective way is to pre-train a model that understands the discourse structure of multi-party dialogues, namely, to whom each utterance is replying. However, due to the lack of explicitly annotated discourse labels in multi-party dialogue corpora, previous works fail to scale up the pre-training process by putting aside the unlabeled multi-party conversational data for nothing. To fully utilize the unlabeled data, we propose to treat the discourse structures as latent variables, then jointly infer them and pre-train the discourse-aware model by unsupervised latent variable inference methods. Experiments on multiple downstream tasks show that our pre-trained model outperforms strong baselines by large margins and achieves state-of-the-art (SOTA) results, justifying the effectiveness of our method. The official implementation of this paper is available at https://github.com/EricLee8/MPD_EMVI.
Anthology ID:
2023.acl-long.533
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9584–9599
Language:
URL:
https://aclanthology.org/2023.acl-long.533
DOI:
10.18653/v1/2023.acl-long.533
Bibkey:
Cite (ACL):
Yiyang Li, Xinting Huang, Wei Bi, and Hai Zhao. 2023. Pre-training Multi-party Dialogue Models with Latent Discourse Inference. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 9584–9599, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Pre-training Multi-party Dialogue Models with Latent Discourse Inference (Li et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2023.acl-long.533.pdf
Video:
 https://preview.aclanthology.org/add_acl24_videos/2023.acl-long.533.mp4