A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering

TL;DR

This paper introduces a graph-guided multi-round retrieval method for conversational open-domain question answering, leveraging passage graphs and relevance feedback to improve retrieval accuracy by modeling answer relations across conversation turns.

Contribution

It proposes a novel graph-guided retrieval approach that models answer relations using passage graphs and incorporates multi-round relevance feedback to enhance conversational QA performance.

Findings

F1 score improved by 5% with predicted history answers.

F1 score improved by 11% with true history answers.

Effective modeling of answer relations enhances retrieval accuracy.

Abstract

In recent years, conversational agents have provided a natural and convenient access to useful information in people's daily life, along with a broad and new research topic, conversational question answering (QA). Among the popular conversational QA tasks, conversational open-domain QA, which requires to retrieve relevant passages from the Web to extract exact answers, is more practical but less studied. The main challenge is how to well capture and fully explore the historical context in conversation to facilitate effective large-scale retrieval. The current work mainly utilizes history questions to refine the current question or to enhance its representation, yet the relations between history answers and the current answer in a conversation, which is also critical to the task, are totally neglected. To address this problem, we propose a novel graph-guided retrieval method to model the relations among answers across conversation turns. In particular, it utilizes a passage graph derived from the hyperlink-connected passages that contains history answers and potential current answers, to retrieve more relevant passages for subsequent answer extraction. Moreover, in order to collect more complementary information in the historical context, we also propose to incorporate the multi-round relevance feedback technique to explore the impact of the retrieval context on current question understanding. Experimental results on the public dataset verify the effectiveness of our proposed method. Notably, the F1 score is improved by 5% and 11% with predicted history answers and true history answers, respectively.