Explicit Alignment and Many-to-many Entailment Based Reasoning for Conversational Machine Reading
This addresses a key bottleneck in CMR for dialogue systems, though it is incremental as it builds on existing methods.
The paper tackles the problem of aligning document and user-provided information in Conversational Machine Reading (CMR) to improve decision-making and follow-up question generation, achieving state-of-the-art micro-accuracy and first place on the ShARC benchmark leaderboard.
Conversational Machine Reading (CMR) requires answering a user's initial question through multi-turn dialogue interactions based on a given document. Although there exist many effective methods, they largely neglected the alignment between the document and the user-provided information, which significantly affects the intermediate decision-making and subsequent follow-up question generation. To address this issue, we propose a pipeline framework that (1) aligns the aforementioned two sides in an explicit way, (2)makes decisions using a lightweight many-to-many entailment reasoning module, and (3) directly generates follow-up questions based on the document and previously asked questions. Our proposed method achieves state-of-the-art in micro-accuracy and ranks the first place on the public leaderboard of the CMR benchmark dataset ShARC.