Zero-Shot Dialogue Disentanglement by Self-Supervised Entangled Response Selection

Ta-Chung Chi, Alexander Rudnicky


Abstract
Dialogue disentanglement aims to group utterances in a long and multi-participant dialogue into threads. This is useful for discourse analysis and downstream applications such as dialogue response selection, where it can be the first step to construct a clean context/response set. Unfortunately, labeling all reply-to links takes quadratic effort w.r.t the number of utterances: an annotator must check all preceding utterances to identify the one to which the current utterance is a reply. In this paper, we are the first to propose a zero-shot dialogue disentanglement solution. Firstly, we train a model on a multi-participant response selection dataset harvested from the web which is not annotated; we then apply the trained model to perform zero-shot dialogue disentanglement. Without any labeled data, our model can achieve a cluster F1 score of 25. We also fine-tune the model using various amounts of labeled data. Experiments show that with only 10% of the data, we achieve nearly the same performance of using the full dataset.
Anthology ID:
2021.emnlp-main.400
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4897–4902
Language:
URL:
https://aclanthology.org/2021.emnlp-main.400
DOI:
10.18653/v1/2021.emnlp-main.400
Bibkey:
Cite (ACL):
Ta-Chung Chi and Alexander Rudnicky. 2021. Zero-Shot Dialogue Disentanglement by Self-Supervised Entangled Response Selection. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4897–4902, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Zero-Shot Dialogue Disentanglement by Self-Supervised Entangled Response Selection (Chi & Rudnicky, EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.400.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.400.mp4
Code
 chijames/zero_shot_dialogue_disentanglement
Data
Ubuntu IRC