Follow-on question suggestion via voice hints for voice assistants

Besnik Fetahu, Pedro Faustini, Anjie Fang, Giuseppe Castellucci, Oleg Rokhlenko, Shervin Malmasi

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


The adoption of voice assistants like Alexa or Siri has grown rapidly, allowing users to instantly access information via voice search. Query suggestion is a standard feature of screen-based search experiences, allowing users to explore additional topics. However, this is not trivial to implement in voice-based settings. To enable this, we tackle the novel task of suggesting questions with compact and natural voice hints to allow users to ask follow-up questions. We define the task, ground it in syntactic theory and outline linguistic desiderata for spoken hints. We propose baselines and an approach using sequence-to-sequence Transformers to generate spoken hints from a list of questions. Using a new dataset of 6681 input questions and human written hints, we evaluated the models with automatic metrics and human evaluation. Results show that a naive approach of concatenating suggested questions creates poor voice hints. Our approach, which applies a linguistically-motivated pretraining task was strongly preferred by humans for producing the most natural hints.
Original languageEnglish
Title of host publicationFindings of the Association for Computational Linguistics
Subtitle of host publicationEMNLP 2023
Place of PublicationStroudsburg
PublisherAssociation for Computational Linguistics
Number of pages16
ISBN (Electronic)9798891760615
Publication statusPublished - 2023
Event2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023 - Singapore, Singapore
Duration: 6 Dec 202310 Dec 2023

Publication series

NameFindings of the Association for Computational Linguistics: EMNLP 2023


Conference2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023


Dive into the research topics of 'Follow-on question suggestion via voice hints for voice assistants'. Together they form a unique fingerprint.

Cite this