Building and Evaluating Open-Domain Dialogue Corpora with Clarifying Questions

TL;DR

This paper introduces a new dataset, benchmarks neural models, and proposes a pipeline for evaluating clarifying questions in open-domain dialogue systems to improve response quality.

Contribution

It presents a novel dataset, benchmarks multiple models, and develops an evaluation pipeline for clarifying questions in open-domain dialogues.

Findings

New dataset for open-domain dialogues with clarifying questions

Benchmark results of state-of-the-art neural models

A pipeline for offline and online evaluation of clarifying questions

Abstract

Enabling open-domain dialogue systems to ask clarifying questions when appropriate is an important direction for improving the quality of the system response. Namely, for cases when a user request is not specific enough for a conversation system to provide an answer right away, it is desirable to ask a clarifying question to increase the chances of retrieving a satisfying answer. To address the problem of 'asking clarifying questions in open-domain dialogues': (1) we collect and release a new dataset focused on open-domain single- and multi-turn conversations, (2) we benchmark several state-of-the-art neural baselines, and (3) we propose a pipeline consisting of offline and online steps for evaluating the quality of clarifying questions in various dialogues. These contributions are suitable as a foundation for further research.