English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Towards Asking Clarification Questions for Information Seeking on Task-Oriented Dialogues (MAS2S)

Forum topic · 小凯 · 2026-07-05

Summary

This paper, by Yue Feng, Hossein A. Rahmani, Aldo Lipani, and Emine Yilmaz (arXiv:2305.13690, May 2023), addresses a key limitation of task-oriented dialogue systems: users often cannot fully describe their complex information needs, and systems may hold ambiguous or missing information about the user. The authors propose MAS2S, a Multi-Attention Seq2Seq Network that can ask clarification questions to resolve uncertainty about a user's information needs and user profile during task-oriented information seeking. They also extend an existing task-oriented information seeking dataset to create Clarit, a publicly released corpus of approximately 100k task-oriented information seeking dialogues. Experiments on Clarit show that MAS2S outperforms baseline models on both clarification question generation and answer prediction tasks. Dataset and code are available at https://github.com/sweetalyssum/clarit. The work is relevant to conversational search, clarification question generation, and personalized information access research.

Towards Asking Clarification Questions for Information Seeking on Task-Oriented Dialogues

Authors: Yue Feng, Hossein A. Rahmani, Aldo Lipani, Emine Yilmaz Published: 2023-05-23 Source: https://arxiv.org/abs/2305.13690 Category: Search Assistance

Overview

Task-oriented dialogue systems aim at providing users with task-specific services. Users of such systems often do not know all the information about the task they are trying to accomplish, requiring them to seek information about the task. To provide accurate and personalized task-oriented information seeking results, task-oriented dialogue systems need to address two potential issues:

1. Users' inability to describe their complex information needs in their requests; 2. Ambiguous/missing information the system has about the users.

Proposed Approach

The authors propose a new Multi-Attention Seq2Seq Network (MAS2S), which can ask questions to clarify the user's information needs and the user's profile in task-oriented information seeking.

Dataset

The paper extends an existing dataset for task-oriented information seeking, producing the Clarit dataset, which contains about 100k task-oriented information seeking dialogues and is publicly available.

  • Dataset and code: https://github.com/sweetalyssum/clarit
  • Results

    Experimental results on Clarit show that MAS2S outperforms baselines on both clarification question generation and answer prediction.

    Related Work

  • Asking Clarification Questions to Handle Ambiguity in Open-Domain QA (arXiv:2305.13808)
  • Asking Clarifying Questions in Open-Domain Information-Seeking Conversations (DOI: 10.1145/3331184.3331265)
  • DiAL: Diversity aware listwise ranking for query auto-complete (EMNLP)
  • Enhancing Discoverability in Enterprise Conversational Systems (arXiv:2412.10933)
  • Evaluating auto-complete ranking for diversity and relevance (ECIR 2021)
  • Evaluation and Continual Improvement for an Enterprise AI Assistant (arXiv:2407.12003)

Tags

#task-oriented-dialogue#clarification-questions#information-seeking#seq2seq#conversational-search#dataset#mas2s

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208958