mlsanityData to 14 Oct 2026

Rewriting the Script: Adapting Text Instructions for Voice Interaction

arXiv 2306.09992 ↗First posted 16 Jun 2023cs.HC cs.CLcited by 5

Not on the map. Why?

Abstract (arXiv)

Voice assistants have sharply risen in popularity in recent years, but their use has been limited mostly to simple applications like music, hands-free search, or control of internet-of-things devices. What would it take for voice assistants to guide people through more complex tasks? In our work, we study the limitations of the dominant approach voice assistants take to complex task guidance: reading aloud written instructions. Using recipes as an example, we observe twelve participants cook at home with a state-of-the-art voice assistant. We learn that the current approach leads to nine challenges, including obscuring the bigger picture, overwhelming users with too much information, and failing to communicate affordances. Instructions delivered by a voice assistant are especially difficult because they cannot be skimmed as easily as written instructions. Alexa in particular did not surface crucial details to the user or answer questions well. We draw on our observations to propose eight ways in which voice assistants can ``rewrite the script'' -- summarizing, signposting, splitting, elaborating, volunteering, reordering, redistributing, and visualizing -- to transform written sources into forms that are readily communicated through spoken conversation. We conclude with a vision of how modern advancements in natural language processing can be leveraged for intelligent agents to guide users effectively through complex tasks.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 20 of its 71 references that are in the map. First posted on arXiv 16 Jun 2023.

Builds on

20 of 71 references.

References · 20

  1. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  2. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
  3. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  4. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 688
  5. 2020TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialoguecited by 185
  6. 2021A Recipe For Arbitrary Text Style Transfer with Large Language Modelscited by 107
  7. 2020Evolution of Semantic Similarity -- A Surveycited by 83
  8. 2020Reasoning about Goals, Steps, and Temporal Ordering with WikiHowcited by 66
  9. 2021Visual Goal-Step Inference using wikiHowcited by 43
  10. 2019What Makes a Good Conversation? Challenges in Designing Truly Conversational Agentscited by 42
  11. 2019Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Textcited by 31
  12. 2021Goal-Oriented Script Constructioncited by 30
8 more
  1. 2017Iris: A Conversational Agent for Complex Taskscited by 22
  2. 2022Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Datacited by 22
  3. 2021BiSECT: Learning to Split and Rephrase Sentences with Bitextscited by 18
  4. 2021Induce, Edit, Retrieve: Language Grounded Multimodal Schema for Instructional Video Retrievalcited by 13
  5. 2021Eliciting and Analysing Users' Envisioned Dialogues with Perfect Voice Assistantscited by 9
  6. 2020Small but Mighty: New Benchmarks for Split and Rephrasecited by 8
  7. 2022Unsupervised Multi-Granularity Summarizationcited by 5
  8. 2019Lessons from Oz: Design Guidelines for Automotive Conversational User Interfacescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 2; 2026: 1.

5 papers.