From Rewriting to Remembering: Common Ground for Conversational QA Models

TL;DR

This paper introduces the Common Ground approach for conversational QA, which accumulates and selects relevant information throughout a conversation, improving efficiency and human-likeness over existing question rewriting methods.

Contribution

The paper proposes the Common Ground method to better leverage conversational context, outperforming current question rewriting techniques in open domain QA.

Findings

Improved accuracy in conversational QA tasks.

More efficient information utilization during conversations.

Enhanced human-like interaction in QA models.

Abstract

In conversational QA, models have to leverage information in previous turns to answer upcoming questions. Current approaches, such as Question Rewriting, struggle to extract relevant information as the conversation unwinds. We introduce the Common Ground (CG), an approach to accumulate conversational information as it emerges and select the relevant information at every turn. We show that CG offers a more efficient and human-like way to exploit conversational information compared to existing approaches, leading to improvements on Open Domain Conversational QA.