Label-Specific Document Representation for Multi-Label Text Classification

IJCNLP 2019  ·  Lin Xiao, Xin Huang, Boli Chen, Liping Jing ·

Multi-label text classification (MLTC) aims to tag most relevant labels for the given document. In this paper, we propose a Label-Specific Attention Network (LSAN) to learn a label-specific document representation. LSAN takes advantage of label semantic information to determine the semantic connection between labels and document for constructing label-specific document representation. Meanwhile, the self-attention mechanism is adopted to identify the label-specific document representation from document content information. In order to seamlessly integrate the above two parts, an adaptive fusion strategy is proposed, which can effectively output the comprehensive label-specific document representation to build multi-label text classifier. Extensive experimental results demonstrate that LSAN consistently outperforms the state-of-the-art methods on four different datasets, especially on the prediction of low-frequency labels. The code and hyper-parameter settings are released to facilitate other researchers.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Multi-Label Text Classification AAPD LSAN P@1 85.28 # 1
P@3 61.12 # 1
P@5 41.84 # 1
nDCG@3 80.84 # 1
nDCG@5 84.78 # 1

Methods


No methods listed for this paper. Add relevant methods here