Label Dependencies-aware Set Prediction Networks for Multi-label Text Classification

arXiv:2304.07022v2 Announce Type: replace
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 …

abstract arxiv classification construct correlation cs.cl dependencies graph labels matrix nature networks prediction set set prediction text text classification type