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