# Answering Unanswered Questions through Semantic Reformulations in Spoken QA

Source: [Answering Unanswered Questions through Semantic Reformulations in Spoken QA](<https://www.sota2.com/research/paper/68fa6fa31e209131cea46d8b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-02T02:58:11.730Z

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

Published: 2023-05-27T07:19:27.000Z

## Abstract

Spoken Question Answering (QA) is a key feature of voice assistants, usually backed by multiple QA systems. Users ask questions via spontaneous speech which can contain disfluencies, errors, and informal syntax or phrasing. This is a major challenge in QA, causing unanswered questions or irrelevant answers, and 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2305.17393>)

[PDF](<https://arxiv.org/pdf/2305.17393.pdf>)
