Task-oriented Domain-specific Meta-Embedding for Text Classification

Xin Wu, Yi Cai, Yang Kai, Tao Wang, Qing Li


Abstract
Meta-embedding learning, which combines complementary information in different word embeddings, have shown superior performances across different Natural Language Processing tasks. However, domain-specific knowledge is still ignored by existing meta-embedding methods, which results in unstable performances across specific domains. Moreover, the importance of general and domain word embeddings is related to downstream tasks, how to regularize meta-embedding to adapt downstream tasks is an unsolved problem. In this paper, we propose a method to incorporate both domain-specific and task-oriented information into meta-embeddings. We conducted extensive experiments on four text classification datasets and the results show the effectiveness of our proposed method.
Anthology ID:
2020.emnlp-main.282
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:
3508–3513
Language:
URL:
https://aclanthology.org/2020.emnlp-main.282
DOI:
10.18653/v1/2020.emnlp-main.282
Bibkey:
Cite (ACL):
Xin Wu, Yi Cai, Yang Kai, Tao Wang, and Qing Li. 2020. Task-oriented Domain-specific Meta-Embedding for Text Classification. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3508–3513, Online. Association for Computational Linguistics.
Cite (Informal):
Task-oriented Domain-specific Meta-Embedding for Text Classification (Wu et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.282.pdf
Video:
 https://slideslive.com/38938998