EnsLM: Ensemble Language Model for Data Diversity by Semantic Clustering

Zhibin Duan, Hao Zhang, Chaojie Wang, Zhengjue Wang, Bo Chen, Mingyuan Zhou


Abstract
Natural language processing (NLP) often faces the problem of data diversity such as different domains, themes, styles, and so on. Therefore, a single language model (LM) is insufficient to learn all knowledge from diverse samples. To solve this problem, we firstly propose an autoencoding topic model with a mixture prior (mATM) to perform clustering for the data, where the clusters defined in semantic space describes the data diversity. Having obtained the clustering assignment for each sample, we develop the ensemble LM (EnsLM) with the technique of weight modulation. Specifically, EnsLM contains a backbone that is adjusted by a few modulated weights to fit for different sample clusters. As a result, the backbone learns the shared knowledge among all clusters while modulated weights extract the cluster-specific features. EnsLM can be trained jointly with mATM with a flexible LM backbone. We evaluate the effectiveness of both mATM and EnsLM on various tasks.
Anthology ID:
2021.acl-long.230
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2954–2967
Language:
URL:
https://aclanthology.org/2021.acl-long.230
DOI:
10.18653/v1/2021.acl-long.230
Bibkey:
Cite (ACL):
Zhibin Duan, Hao Zhang, Chaojie Wang, Zhengjue Wang, Bo Chen, and Mingyuan Zhou. 2021. EnsLM: Ensemble Language Model for Data Diversity by Semantic Clustering. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2954–2967, Online. Association for Computational Linguistics.
Cite (Informal):
EnsLM: Ensemble Language Model for Data Diversity by Semantic Clustering (Duan et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.230.pdf
Video:
 https://aclanthology.org/2021.acl-long.230.mp4
Code
 bochengroup/enslm
Data
IMDb Movie ReviewsMS COCO