Beyond Static: Related Questions Retrieval Through Conversations in Community Question Answering

TL;DR

This paper introduces TeCQR, a conversational model for related question retrieval in community Q&A platforms that leverages tag-enhanced clarifying questions and a noise-tolerance mechanism to improve accuracy.

Contribution

The paper proposes a novel conversational retrieval model that incorporates tag-enhanced clarifying questions and a two-stage training process for better question similarity detection.

Findings

TeCQR significantly outperforms existing baselines in related question retrieval tasks.

The model effectively handles noisy feedback through a noise tolerance mechanism.

Conversational context improves the precision of related question retrieval.

Abstract

In community question answering (cQA) platforms like Stack Overflow, related question retrieval is recognized as a fundamental task that allows users to retrieve related questions to answer user queries automatically. Although many traditional approaches have been proposed for investigating this research field, they mostly rely on static approaches and neglect the interaction property. We argue that the conversational way can well distinguish the fine-grained representations of questions and has great potential to improve the performance of question retrieval. In this paper, we propose a related question retrieval model through conversations, called TeCQR, to locate related questions in cQA. Specifically, we build conversations by utilizing tag-enhanced clarifying questions (CQs). In addition, we design a noise tolerance model that evaluates the semantic similarity between questions and tags, enabling the model to effectively handle noisy feedback. Moreover, the tag-enhanced two-stage offline training is proposed to fully exploit the mutual relationships among user queries, questions, and tags to learn their fine-grained representations. Based on the learned representations and contextual conversations, TeCQR incorporates conversational feedback by learning to ask tag-enhanced clarifying questions to retrieve related questions more effectively. Experimental results demonstrate that our model significantly outperforms state-of-the-art baselines.