Response Selection for Multi-Party Conversations with Dynamic Topic Tracking
Wang, Weishi, Joty, Shafiq, Hoi, Steven C. H.
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Oct-15-2020
- Country:
- Oceania > Australia
- North America > United States
- Texas > Travis County
- Austin (0.04)
- New York > New York County
- New York City (0.04)
- Texas > Travis County
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- Asia
- Singapore (0.04)
- Myanmar > Tanintharyi Region
- Dawei (0.04)
- Genre:
- Research Report (0.64)
- Industry:
- Information Technology > Software (0.50)
- Technology: