BIT-WOW at NLPCC-2022 Task5 Track1: Hierarchical Multi-label Classification via Label-Aware Graph Convolutional Network

Bo Wang, Yi-Fan Lu, Xiaochi Wei, Xiao Liu, Ge Shi, Changsen Yuan, Heyan Huang, Chong Feng, Xianling Mao

Abstract: This paper describes the system proposed by the BIT-WOW team for NLPCC2022 shared task in Task5 Track1. The track is about multi-label towards abstracts of academic papers in scientific domain, which includes hierarchical dependencies among 1,530 labels. In order to distinguish semantic information among hierarchical label structures, we propose the Label-aware Graph Convolutional Network (LaGCN), which uses Graph Convolutional Network to capture the label association through context-based label embedding. Besides, curriculum learning is applied for domain adaptation and to mitigate the impact of a large number of categories. The experiments show that: 1) LaGCN effectively models the category information and makes a considerable improvement in dealing with a large number of categories; 2) Curriculum learning is beneficial for a single model in the complex task. Our best results were obtained by an ensemble model. According to the official results, our approach proved the best in this track.