Abstract
While participants in a multi-party multi-turn conversation simultaneously engage in multiple conversation topics, existing response selection methods are developed mainly focusing on a two-party single-conversation scenario. Hence, the prolongation and transition of conversation topics are ignored by current methods. In this work, we frame response selection as a dynamic topic tracking task to match the topic between the response and relevant conversation context. With this new formulation, we propose a novel multi-task learning framework that supports efficient encoding through large pretrained models with only two utterances at once to perform dynamic topic disentanglement and response selection. We also propose Topic-BERT an essential pretraining step to embed topic information into BERT with self-supervised learning. Experimental results on the DSTC-8 Ubuntu IRC dataset show state-of-the-art results in response selection and topic disentanglement tasks outperforming existing methods by a good margin.- Anthology ID:
- 2020.emnlp-main.533
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6581–6591
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.533
- DOI:
- 10.18653/v1/2020.emnlp-main.533
- Cite (ACL):
- Weishi Wang, Steven C.H. Hoi, and Shafiq Joty. 2020. Response Selection for Multi-Party Conversations with Dynamic Topic Tracking. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6581–6591, Online. Association for Computational Linguistics.
- Cite (Informal):
- Response Selection for Multi-Party Conversations with Dynamic Topic Tracking (Wang et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2020.emnlp-main.533.pdf