Hierarchical Text Classification with Reinforced Label Assignment

Yuning Mao, Jingjing Tian, Jiawei Han, Xiang Ren

Abstract
While existing hierarchical text classification (HTC) methods attempt to capture label hierarchies for model training, they either make local decisions regarding each label or completely ignore the hierarchy information during inference. To solve the mismatch between training and inference as well as modeling label dependencies in a more principled way, we formulate HTC as a Markov decision process and propose to learn a Label Assignment Policy via deep reinforcement learning to determine where to place an object and when to stop the assignment process. The proposed method, HiLAP, explores the hierarchy during both training and inference time in a consistent manner and makes inter-dependent decisions. As a general framework, HiLAP can incorporate different neural encoders as base models for end-to-end training. Experiments on five public datasets and four base models show that HiLAP yields an average improvement of 33.4% in Macro-F1 over flat classifiers and outperforms state-of-the-art HTC methods by a large margin. Data and code can be found at https://github.com/morningmoni/HiLAP.
Anthology ID:
D19-1042
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
445–455
Language:
URL:
https://aclanthology.org/D19-1042
DOI:
10.18653/v1/D19-1042
Bibkey:
Cite (ACL):
Yuning Mao, Jingjing Tian, Jiawei Han, and Xiang Ren. 2019. Hierarchical Text Classification with Reinforced Label Assignment. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 445–455, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Hierarchical Text Classification with Reinforced Label Assignment (Mao et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp22-frontmatter/D19-1042.pdf
Attachment:
 D19-1042.Attachment.zip
Code
 morningmoni/HiLAP
Data
New York Times Annotated Corpus, RCV1
PDF Search Code Attachment