Adaptation of Hierarchical Structured Models for Speech Act Recognition in Asynchronous Conversation

Tasnim Mohiuddin, Thanh-Tung Nguyen, Shafiq Joty


Abstract
We address the problem of speech act recognition (SAR) in asynchronous conversations (forums, emails). Unlike synchronous conversations (e.g., meetings, phone), asynchronous domains lack large labeled datasets to train an effective SAR model. In this paper, we propose methods to effectively leverage abundant unlabeled conversational data and the available labeled data from synchronous domains. We carry out our research in three main steps. First, we introduce a neural architecture based on hierarchical LSTMs and conditional random fields (CRF) for SAR, and show that our method outperforms existing methods when trained on in-domain data only. Second, we improve our initial SAR models by semi-supervised learning in the form of pretrained word embeddings learned from a large unlabeled conversational corpus. Finally, we employ adversarial training to improve the results further by leveraging the labeled data from synchronous domains and by explicitly modeling the distributional shift in two domains.
Anthology ID:
N19-1134
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1326–1336
Language:
URL:
https://aclanthology.org/N19-1134
DOI:
10.18653/v1/N19-1134
Bibkey:
Cite (ACL):
Tasnim Mohiuddin, Thanh-Tung Nguyen, and Shafiq Joty. 2019. Adaptation of Hierarchical Structured Models for Speech Act Recognition in Asynchronous Conversation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1326–1336, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Adaptation of Hierarchical Structured Models for Speech Act Recognition in Asynchronous Conversation (Mohiuddin et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1134.pdf