# Follow-on Question Suggestion via Voice Hints for Voice Assistants

arXiv: https://arxiv.org/abs/2310.17034 · HTML: https://mlsanity.com/paper/2310.17034/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 43 references that are in the map.
- First posted on arXiv 25 Oct 2023.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [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)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [Neural Text Summarization: A Critical Evaluation](https://mlsanity.com/paper/1908.08960/) (2019)
- [Unsupervised Evaluation of Interactive Dialog with DialoGPT](https://mlsanity.com/paper/2006.12719/) (2020)
- [Efficient One-Pass End-to-End Entity Linking for Questions](https://mlsanity.com/paper/2010.02413/) (2020)
- [Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints](https://mlsanity.com/paper/1603.08887/) (2016)
- [Diversifying Dialogue Generation with Non-Conversational Text](https://mlsanity.com/paper/2005.04346/) (2020)
- [ChainCQG: Flow-Aware Conversational Question Generation](https://mlsanity.com/paper/2102.02864/) (2021)
- [Reinforced Dynamic Reasoning for Conversational Question Generation](https://mlsanity.com/paper/1907.12667/) (2019)
- [Rethinking End-to-End Evaluation of Decomposable Tasks: A Case Study on Spoken Language Understanding](https://mlsanity.com/paper/2106.15065/) (2021)
- [Closed-Book Training to Improve Summarization Encoder Memory](https://mlsanity.com/paper/1809.04585/) (2018)
- [Challenges in Supporting Exploratory Search through Voice Assistants](https://mlsanity.com/paper/2003.02986/) (2020)

## Built on by (most cited first, 2 of 2)

- [Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers](https://mlsanity.com/paper/2406.05255/) (2024)
- [Identifying Shopping Intent in Product QA for Proactive Recommendations](https://mlsanity.com/paper/2404.06017/) (2024)

## Abstract (arXiv)

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.