Asking Multimodal Clarifying Questions in Mixed-Initiative Conversational Search

TL;DR

This paper introduces a novel multimodal approach to improve clarifying questions in conversational search by incorporating images, leading to significant performance gains and a new dataset for research.

Contribution

It proposes the task of asking multimodal clarifying questions, introduces the Melon dataset, and develops the Marto model with a prompt-based training strategy.

Findings

Adding images improves retrieval performance by up to 90%.

Marto outperforms discriminative baselines in effectiveness and efficiency.

The dataset Melon contains over 4,000 multimodal questions with 14,000 images.

Abstract

In mixed-initiative conversational search systems, clarifying questions are used to help users who struggle to express their intentions in a single query. These questions aim to uncover user's information needs and resolve query ambiguities. We hypothesize that in scenarios where multimodal information is pertinent, the clarification process can be improved by using non-textual information. Therefore, we propose to add images to clarifying questions and formulate the novel task of asking multimodal clarifying questions in open-domain, mixed-initiative conversational search systems. To facilitate research into this task, we collect a dataset named Melon that contains over 4k multimodal clarifying questions, enriched with over 14k images. We also propose a multimodal query clarification model named Marto and adopt a prompt-based, generative fine-tuning strategy to perform the training of different stages with different prompts. Several analyses are conducted to understand the importance of multimodal contents during the query clarification phase. Experimental results indicate that the addition of images leads to significant improvements of up to 90% in retrieval performance when selecting the relevant images. Extensive analyses are also performed to show the superiority of Marto compared with discriminative baselines in terms of effectiveness and efficiency.