# Answering Unanswered Questions through Semantic Reformulations in Spoken QA

arXiv: https://arxiv.org/abs/2305.17393 · HTML: https://mlsanity.com/paper/2305.17393/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 44 references that are in the map.
- First posted on arXiv 27 May 2023.

## Builds on (most cited first, 18 of 18)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Decontextualization: Making Sentences Stand-Alone](https://mlsanity.com/paper/2102.05169/) (2021)
- [Controllable Sentence Simplification](https://mlsanity.com/paper/1910.02677/) (2019)
- [What Kind of Language Is Hard to Language-Model?](https://mlsanity.com/paper/1906.04726/) (2019)
- [Ask the Right Questions: Active Question Reformulation with Reinforcement Learning](https://mlsanity.com/paper/1705.07830/) (2017)
- [Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering](https://mlsanity.com/paper/2101.00391/) (2021)
- [Inquisitive Question Generation for High Level Text Comprehension](https://mlsanity.com/paper/2010.01657/) (2020)
- [Fluent Translations from Disfluent Speech in End-to-End Speech Translation](https://mlsanity.com/paper/1906.00556/) (2019)
- [Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering](https://mlsanity.com/paper/2106.04016/) (2021)
- [Reinforced Question Rewriting for Conversational Question Answering](https://mlsanity.com/paper/2210.15777/) (2022)
- [SemEval-2023 Task 2: Fine-grained Multilingual Named Entity Recognition (MultiCoNER 2)](https://mlsanity.com/paper/2305.06586/) (2023)
- [How to Ask Better Questions? A Large-Scale Multi-Domain Dataset for Rewriting Ill-Formed Questions](https://mlsanity.com/paper/1911.09247/) (2019)
- [Generative Question Refinement with Deep Reinforcement Learning in Retrieval-based QA System](https://mlsanity.com/paper/1908.05604/) (2019)

## Built on by (most cited first, 3 of 3)

- [Instant Answering in E-Commerce Buyer-Seller Messaging using Message-to-Question Reformulation](https://mlsanity.com/paper/2401.09785/) (2024)
- [Identifying Shopping Intent in Product QA for Proactive Recommendations](https://mlsanity.com/paper/2404.06017/) (2024)
- [Rewrite What Matters: Adaptive Multilingual Query Rewriting for Reasoning via Agentic Reinforcement Learning](https://mlsanity.com/paper/2610.04899/) (2026)

## Abstract (arXiv)

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.