%0 Conference Proceedings %T Response Selection for Multi-Party Conversations with Dynamic Topic Tracking %A Wang, Weishi %A Hoi, Steven C.H. %A Joty, Shafiq %Y Webber, Bonnie %Y Cohn, Trevor %Y He, Yulan %Y Liu, Yang %S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) %D 2020 %8 November %I Association for Computational Linguistics %C Online %F wang-etal-2020-response %X 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. %R 10.18653/v1/2020.emnlp-main.533 %U https://aclanthology.org/2020.emnlp-main.533 %U https://doi.org/10.18653/v1/2020.emnlp-main.533 %P 6581-6591