HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization

Zhongfen Deng, Hao Peng, Dongxiao He, Jianxin Li, Philip Yu


Abstract
The current state-of-the-art model HiAGM for hierarchical text classification has two limitations. First, it correlates each text sample with all labels in the dataset which contains irrelevant information. Second, it does not consider any statistical constraint on the label representations learned by the structure encoder, while constraints for representation learning are proved to be helpful in previous work. In this paper, we propose HTCInfoMax to address these issues by introducing information maximization which includes two modules: text-label mutual information maximization and label prior matching. The first module can model the interaction between each text sample and its ground truth labels explicitly which filters out irrelevant information. The second one encourages the structure encoder to learn better representations with desired characteristics for all labels which can better handle label imbalance in hierarchical text classification. Experimental results on two benchmark datasets demonstrate the effectiveness of the proposed HTCInfoMax.
Anthology ID:
2021.naacl-main.260
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3259–3265
Language:
URL:
https://aclanthology.org/2021.naacl-main.260
DOI:
10.18653/v1/2021.naacl-main.260
Bibkey:
Cite (ACL):
Zhongfen Deng, Hao Peng, Dongxiao He, Jianxin Li, and Philip Yu. 2021. HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3259–3265, Online. Association for Computational Linguistics.
Cite (Informal):
HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization (Deng et al., NAACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-3/2021.naacl-main.260.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-3/2021.naacl-main.260.mp4
Code
 RingBDStack/HTCInfoMax
Data
RCV1WOS