MINGYU DEREK MA
MINGYU DEREK MA
Home
News
Publications
CV
Resources
Light
Dark
Automatic
Parameter-Efficient Learning
Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning
We use soft prompt tokens to learn task properties, incorporate segment information and reiterate the task before predicting value. Our method drastically reduces the number of parameters needed to less than 0.5% of prior works while achieving better low-resource dialogue state tracking performance.
Mingyu Derek Ma
,
Jiun-Yu Kao
,
Shuyang Gao
,
Arpit Gupta
,
Di Jin
,
Tagyoung Chung
,
Nanyun Peng
PDF
Cite
Poster
Slides
Video
DOI
ISCA Archive
ISCA PDF
Amazon Science
Cite
×