2021/10/28 by Hadrien Lautraite, Lautraite, Hadrien, Nada Naji +8
Computer Science · #Artificial intelligence #Computation and Language (cs.CL) #Computer science #Context (archaeology) #FOS: Computer and information sciences #Human–computer interaction #Information needs #Information retrieval #Information system #Key (lock) #Mechanism (biology) #Multimodal Machine Learning Applications #Question answering #Scope (computer science) #Selection (genetic algorithm) #Speech and dialogue systems #Topic Modeling #User information #World Wide Web #cs.CL
paper · pdf · doi:10.48550/arxiv.2110.15235
published in arXiv (Cornell University) (Cornell University) · 9 pages, 3 figures, 2 tables
arxiv created 2021/10/28 · openalex publication_date 2021/10/28 · arxiv updated 2021/10/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Clarification resolution plays an important role in various information\nretrieval tasks such as interactive question answering and conversational\nsearch. In such context, the user often formulates their information needs as\nshort and ambiguous queries, some popular search interfaces then prompt the\nuser to confirm her intent (e.g. "Did you mean ... ?") or to rephrase if\nneeded. When it comes to dialogue systems, having fluid user-bot exchanges is\nkey to good user experience. In the absence of such clarification mechanism,\none of the following responses is given to the user: 1) A direct answer, which\ncan potentially be non-relevant if the intent was not clear, 2) a generic\nfallback message informing the user that the retrieval tool is incapable of\nhandling the query. Both scenarios might raise frustration and degrade the user\nexperience. To this end, we propose a multi-stage clarification mechanism for\nprompting clarification and query selection in the context of a question\nanswering dialogue system. We show that our proposed mechanism improves the\noverall user experience and outperforms competitive baselines with two\ndatasets, namely the public in-scope out-of-scope dataset and a commercial\ndataset based on real user logs.\n