Hierarchical Text Classification with Reinforced Label Assignment

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.

EMNLP 2019

References in corpus (5)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Convolutional Neural Networks for Sentence Classification
• Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
• Weakly-Supervised Neural Text Classification
• LSHTC: A Benchmark for Large-Scale Text Classification

Cited by in corpus (15)

• Multi-Label Text Classification using Attention-based Graph Neural Network
• Hierarchical Interdisciplinary Topic Detection Model for Research Proposal Classification
• Octet: Online Catalog Taxonomy Enrichment with Self-Supervision
• Hierarchical Text Classification As Sub-Hierarchy Sequence Generation
• Efficient strategies for hierarchical text classification: External knowledge and auxiliary tasks
• Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning
• Hierarchical Text Classification of Urdu News using Deep Neural Network
• LA-HCN: Label-based Attention for Hierarchical Multi-label TextClassification Neural Network
• Modeling Text-Label Alignment for Hierarchical Text Classification
• Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning
• Hierarchy-Aware T5 with Path-Adaptive Mask Mechanism for Hierarchical Text Classification
• Taxonomy Completion via Triplet Matching Network
• Hierarchical Metadata-Aware Document Categorization under Weak Supervision
• Hierarchical Text Classification Using Contrastive Learning Informed Path Guided Hierarchy
• MATCH: Metadata-Aware Text Classification in A Large Hierarchy