REVIEW 2 cited by
Response Selection for Multi-Party Conversations with Dynamic Topic Tracking
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 2 Pith papers
-
Advancing Multi-Party Dialogue Framework with Speaker-ware Contrastive Learning
CMR improves multi-party response generation by contrastively learning speaker styles in a first stage and jointly training response generation with contrastive objectives in a second stage.
-
Multi-Party Conversational Agents: A Survey
A survey of multi-party conversational AI that organizes tasks into state-of-mind modeling, semantic understanding, and action modeling, and argues that theory of mind is the key missing ingredient.
Discussion (0). Continue with ORCID to comment.