Year: 2023
Type: preprint
Abstract: Multi-label text classification involves extracting all relevant labels from a sentence. Given the unordered nature of these labels, we propose approaching the problem as a set prediction task. To address the correlation between labels, we leverage Graph Convolutional Networks and construct an adjacency matrix based on the statistical relations between labels. Additionally, we enhance recall ability by applying the Bhattacharyya distance to the output distributions of the set prediction networks. We evaluate the effectiveness of our approach on two multi-label datasets and demonstrate its superiority over previous baselines through experimental results.
Source: arXiv (Cornell University)
Authors: Xinkai, Du, Quanjie, Han, Yalin, Sun, Chao, Lv, Maosong, Sun
Institution: Tsinghua University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4366198232