Follow-on Question Suggestion via Voice Hints for Voice Assistants

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


Abstract
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.
Anthology ID:
2023.findings-emnlp.24
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
310–325
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.24
DOI:
10.18653/v1/2023.findings-emnlp.24
Bibkey:
Cite (ACL):
Besnik Fetahu, Pedro Faustini, Anjie Fang, Giuseppe Castellucci, Oleg Rokhlenko, and Shervin Malmasi. 2023. Follow-on Question Suggestion via Voice Hints for Voice Assistants. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 310–325, Singapore. Association for Computational Linguistics.
Cite (Informal):
Follow-on Question Suggestion via Voice Hints for Voice Assistants (Fetahu et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.24.pdf