SkipWriter: LLM-Powered Abbreviated Writing on Tablets

要旨

Large Language Models (LLMs) may offer transformative opportunities for text input, especially for physically demanding modalities like handwriting. We studied a form of abbreviated handwriting by designing, developing, and evaluating a prototype, named SkipWriter, that converts handwritten strokes of a variable-length prefix-based abbreviation (e.g. "ho a y" as handwritten strokes) into the intended full phrase (e.g., "how are you" in the digital format) based on the preceding context. SkipWriter consists of an in-production handwriting recognizer and an LLM fine-tuned on this task. With flexible pen input, SkipWriter allows the user to add and revise prefix strokes when predictions do not match the user's intent. An user evaluation demonstrated a 60% reduction in motor movements with an average speed of 25.78 WPM. We also showed that this reduction is close to the ceiling of our model in an offline simulation.

著者
Zheer Xu
Dartmouth College, Hanover, New Hampshire, United States
Shanqing Cai
Google, Mountain View, California, United States
Mukund Varma T
UC San Diego, La Jolla, California, United States
Subhashini Venugopalan
Google, Mountain View, California, United States
Shumin Zhai
Google, Mountain View, California, United States
論文URL

https://doi.org/10.1145/3654777.3676423

動画

会議: UIST 2024

ACM Symposium on User Interface Software and Technology

セッション: 3. Manipulating Text

Westin: Allegheny 3
4 件の発表
2024-10-14 22:40:00
2024-10-14 23:40:00