Answering unanswered questions through semantic reformulations in Spoken QA

Pedro Faustini, Zhiyu Chen, Besnik Fetahu, Oleg Rokhlenko, Shervin Malmasi

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

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.
Original languageEnglish
Title of host publicationProceedings of the 61st Annual Meeting of the Association for Computational Linguistics volume 5
Subtitle of host publicationIndustry Track
Place of PublicationStroudsburg
PublisherAssociation for Computational Linguistics
Pages729-743
Number of pages15
ISBN (Electronic)9781959429685
DOIs
Publication statusPublished - 2023
EventAnnual Meeting of the Association for Computational Linguistics (61st : 2023) - Toronto, Canada
Duration: 9 Jul 202314 Jul 2023
Conference number: 61st
https://2023.aclweb.org/

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
Volume5
ISSN (Print)0736-587X

Conference

ConferenceAnnual Meeting of the Association for Computational Linguistics (61st : 2023)
Abbreviated titleACL'23
Country/TerritoryCanada
CityToronto
Period9/07/2314/07/23
Internet address

Fingerprint

Dive into the research topics of 'Answering unanswered questions through semantic reformulations in Spoken QA'. Together they form a unique fingerprint.

Cite this