Abstract
This paper investigates pre-trained language models to find out which model intrinsically carries the most informative representation for task-oriented dialogue tasks. We approach the problem from two aspects: supervised classifier probe and unsupervised mutual information probe. We fine-tune a feed-forward layer as the classifier probe on top of a fixed pre-trained language model with annotated labels in a supervised way. Meanwhile, we propose an unsupervised mutual information probe to evaluate the mutual dependence between a real clustering and a representation clustering. The goals of this empirical paper are to 1) investigate probing techniques, especially from the unsupervised mutual information aspect, 2) provide guidelines of pre-trained language model selection for the dialogue research community, 3) find insights of pre-training factors for dialogue application that may be the key to success.- Anthology ID:
- 2020.emnlp-main.409
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5036–5051
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.409
- DOI:
- 10.18653/v1/2020.emnlp-main.409
- Cite (ACL):
- Chien-Sheng Wu and Caiming Xiong. 2020. Probing Task-Oriented Dialogue Representation from Language Models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5036–5051, Online. Association for Computational Linguistics.
- Cite (Informal):
- Probing Task-Oriented Dialogue Representation from Language Models (Wu & Xiong, EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2020.emnlp-main.409.pdf