Online Conversation Disentanglement with Pointer Networks

Tao Yu, Shafiq Joty


Abstract
Huge amounts of textual conversations occur online every day, where multiple conversations take place concurrently. Interleaved conversations lead to difficulties in not only following the ongoing discussions but also extracting relevant information from simultaneous messages. Conversation disentanglement aims to separate intermingled messages into detached conversations. However, existing disentanglement methods rely mostly on handcrafted features that are dataset specific, which hinders generalization and adaptability. In this work, we propose an end-to-end online framework for conversation disentanglement that avoids time-consuming domain-specific feature engineering. We design a novel way to embed the whole utterance that comprises timestamp, speaker, and message text, and propose a custom attention mechanism that models disentanglement as a pointing problem while effectively capturing inter-utterance interactions in an end-to-end fashion. We also introduce a joint-learning objective to better capture contextual information. Our experiments on the Ubuntu IRC dataset show that our method achieves state-of-the-art performance in both link and conversation prediction tasks.
Anthology ID:
2020.emnlp-main.512
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6321–6330
Language:
URL:
https://aclanthology.org/2020.emnlp-main.512
DOI:
10.18653/v1/2020.emnlp-main.512
Bibkey:
Cite (ACL):
Tao Yu and Shafiq Joty. 2020. Online Conversation Disentanglement with Pointer Networks. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6321–6330, Online. Association for Computational Linguistics.
Cite (Informal):
Online Conversation Disentanglement with Pointer Networks (Yu & Joty, EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.512.pdf
Video:
 https://slideslive.com/38939000