Answering Unanswered Questions through Semantic Reformulations in Spoken QA
Pedro Faustini, Zhiyu Chen, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi
Abstract
Spoken Question Answering (QA) is a key feature of voice assistants, usually backed by multiple QA systems. Users ask questions via spontaneous speech that can contain disfluencies, errors, and informal syntax or phrasing. This is a major challenge in QA, causing unanswered questions or irrelevant answers, leading to bad user experiences. We analyze failed QA requests to identify core challenges: lexical gaps, proposition types, complex syntactic structure, and high specificity. We propose a Semantic Question Reformulation (SURF) model offering three linguistically-grounded operations (repair, syntactic reshaping, generalization) to rewrite questions to facilitate answering. Offline evaluation on 1M unanswered questions from a leading voice assistant shows that SURF significantly improves answer rates: up to 24% of previously unanswered questions obtain relevant answers (75%). Live deployment shows positive impact for millions of customers with unanswered questions; explicit relevance feedback shows high user satisfaction.
BibTeX
@inproceedings{faustini-etal-2023-answering,
title = "Answering Unanswered Questions through Semantic Reformulations in Spoken {QA}",
author = "Faustini, Pedro and
Chen, Zhiyu and
Fetahu, Besnik and
Rokhlenko, Oleg and
Malmasi, Shervin",
editor = "Sitaram, Sunayana and
Beigman Klebanov, Beata and
Williams, Jason D",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-industry.70/",
doi = "10.18653/v1/2023.acl-industry.70",
pages = "729--743"
}