Hierarchical Text Classification with Reinforced Label Assignment

08/27/2019
by   Yuning Mao, et al.
0

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 state-of-the-art HTC methods by a large margin. Data and code can be found at https://github.com/morningmoni/HiLAP.

READ FULL TEXT
research
05/05/2022

Exploiting Global and Local Hierarchies for Hierarchical Text Classification

Hierarchical text classification aims to leverage label hierarchy in mul...
research
03/08/2022

Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification

Hierarchical text classification is a challenging subtask of multi-label...
research
07/06/2018

JUMPER: Learning When to Make Classification Decisions in Reading

In early years, text classification is typically accomplished by feature...
research
07/07/2011

Text Classification: A Sequential Reading Approach

We propose to model the text classification process as a sequential deci...
research
05/20/2018

Abstractive Text Classification Using Sequence-to-convolution Neural Networks

We propose a new deep neural network model and its training scheme for t...
research
11/22/2021

Hierarchy Decoder is All You Need To Text Classification

Hierarchical text classification (HTC) to a taxonomy is essential for va...
research
12/09/2022

HieNet: Bidirectional Hierarchy Framework for Automated ICD Coding

International Classification of Diseases (ICD) is a set of classificatio...

Please sign up or login with your details

Forgot password? Click here to reset