ISCA Archive Interspeech 2023
ISCA Archive Interspeech 2023

Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning

Mingyu Derek Ma, Jiun-Yu Kao, Shuyang Gao, Arpit Gupta, Di Jin, Tagyoung Chung, Nanyun Peng

Dialogue state tracking (DST) is an important step in dialogue management to keep track of users' beliefs. Existing works fine-tune all language model (LM) parameters to tackle the DST task, which requires significant data and computing resources for training and hosting. The cost grows exponentially in the real-world deployment where dozens of fine-tuned LM are used for different domains and tasks. To reduce parameter size and better utilize cross-task shared information, we propose to use soft prompt token embeddings to learn task properties. Without tuning LM parameters, our method drastically reduces the number of parameters needed to less than 0.5% of prior works while achieving better low-resource DST performance.

doi: 10.21437/Interspeech.2023-2238

Cite as: Ma, M.D., Kao, J.-Y., Gao, S., Gupta, A., Jin, D., Chung, T., Peng, N. (2023) Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning. Proc. INTERSPEECH 2023, 4653-4657, doi: 10.21437/Interspeech.2023-2238

  author={Mingyu Derek Ma and Jiun-Yu Kao and Shuyang Gao and Arpit Gupta and Di Jin and Tagyoung Chung and Nanyun Peng},
  title={{Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning}},
  booktitle={Proc. INTERSPEECH 2023},