ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension
This work addresses inefficiencies in multi-step conversational AI systems for researchers and practitioners, though it is incremental as it builds on existing T5 models with a shared parameter mechanism.
The authors tackled the problem of conversational machine reading comprehension by proposing ET5, an end-to-end framework that integrates decision making, span extraction, and question rephrasing to reduce information gaps, achieving a state-of-the-art BLEU-4 score of 55.2 on the ShARC leaderboard.
Conversational machine reading comprehension (CMRC) aims to assist computers to understand an natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text. Existing methods typically require three steps: (1) decision making based on entailment reasoning; (2) span extraction if required by the above decision; (3) question rephrasing based on the extracted span. However, for nearly all these methods, the span extraction and question rephrasing steps cannot fully exploit the fine-grained entailment reasoning information in decision making step because of their relative independence, which will further enlarge the information gap between decision making and question phrasing. Thus, to tackle this problem, we propose a novel end-to-end framework for conversational machine reading comprehension based on shared parameter mechanism, called entailment reasoning T5 (ET5). Despite the lightweight of our proposed framework, experimental results show that the proposed ET5 achieves new state-of-the-art results on the ShARC leaderboard with the BLEU-4 score of 55.2. Our model and code are publicly available at https://github.com/Yottaxx/ET5.