Bridging The Gap: Entailment Fused-T5 for Open-retrieval Conversational Machine Reading Comprehension

TL;DR

This paper introduces Entailment Fused-T5, an end-to-end model that improves open-retrieval conversational machine reading comprehension by bridging the information gap between decision-making and question generation, achieving state-of-the-art results.

Contribution

The paper proposes a novel one-stage end-to-end framework, Entailment Fused-T5, that unifies decision-making and question generation for better performance.

Findings

Achieves state-of-the-art performance on OR-ShARC benchmark.

Effectively bridges the information gap in conversational machine reading.

Demonstrates the benefits of global understanding in decision and generation tasks.

Abstract

Open-retrieval conversational machine reading comprehension (OCMRC) simulates real-life conversational interaction scenes. Machines are required to make a decision of "Yes/No/Inquire" or generate a follow-up question when the decision is "Inquire" based on retrieved rule texts, user scenario, user question, and dialogue history. Recent studies explored the methods to reduce the information gap between decision-making and question generation and thus improve the performance of generation. However, the information gap still exists because these pipeline structures are still limited in decision-making, span extraction, and question rephrasing three stages. Decision-making and generation are reasoning separately, and the entailment reasoning utilized in decision-making is hard to share through all stages. To tackle the above problem, we proposed a novel one-stage end-to-end framework, called Entailment Fused-T5 (EFT), to bridge the information gap between decision-making and generation in a global understanding manner. The extensive experimental results demonstrate that our proposed framework achieves new state-of-the-art performance on the OR-ShARC benchmark.