Dual Process Masking for Dialogue Act Recognition
Yeo Jin Kim, Halim Acosta, Wookhee Min, Jonathan Rowe, Bradford Mott, Snigdha Chaturvedi, James Lester
Abstract
Dialogue act recognition is the task of classifying conversational utterances based on their communicative intent or function. To address this problem, we propose a novel two-phase processing approach called Dual-Process Masking. This approach streamlines the task by masking less important tokens in the input, identified through retrospective analysis of their estimated contribution during training. It enhances interpretability by using the masks applied during classification learning. Dual-Process Masking significantly improves performance over strong baselines for dialogue act recognition on a collaborative problem-solving dataset and three public dialogue benchmarks.
BibTeX
@inproceedings{kim-etal-2024-dual,
title = "Dual Process Masking for Dialogue Act Recognition",
author = "Kim, Yeo Jin and
Acosta, Halim and
Min, Wookhee and
Rowe, Jonathan and
Mott, Bradford and
Chaturvedi, Snigdha and
Lester, James",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.895/",
doi = "10.18653/v1/2024.findings-emnlp.895",
pages = "15270--15283"
}