MatchXML: An Efficient Text-label Matching Framework for Extreme Multi-label Text Classification

TL;DR

MatchXML introduces an efficient framework for extreme multi-label text classification by combining semantic dense label embeddings, hierarchical label trees, and multi-representation text features, achieving state-of-the-art accuracy and speed.

Contribution

It proposes MatchXML, a novel approach that integrates dense label embeddings, hierarchical clustering, and multi-faceted text representations for improved XMC performance.

Findings

Achieves state-of-the-art accuracy on five datasets

Outperforms competitors in speed across all datasets

Effectively combines dense and sparse features for classification

Abstract

The eXtreme Multi-label text Classification(XMC) refers to training a classifier that assigns a text sample with relevant labels from an extremely large-scale label set (e.g., millions of labels). We propose MatchXML, an efficient text-label matching framework for XMC. We observe that the label embeddings generated from the sparse Term Frequency-Inverse Document Frequency(TF-IDF) features have several limitations. We thus propose label2vec to effectively train the semantic dense label embeddings by the Skip-gram model. The dense label embeddings are then used to build a Hierarchical Label Tree by clustering. In fine-tuning the pre-trained encoder Transformer, we formulate the multi-label text classification as a text-label matching problem in a bipartite graph. We then extract the dense text representations from the fine-tuned Transformer. Besides the fine-tuned dense text embeddings, we also extract the static dense sentence embeddings from a pre-trained Sentence Transformer. Finally, a linear ranker is trained by utilizing the sparse TF-IDF features, the fine-tuned dense text representations and static dense sentence features. Experimental results demonstrate that MatchXML achieves state-of-the-art accuracy on five out of six datasets. As for the speed, MatchXML outperforms the competing methods on all the six datasets. Our source code is publicly available at https://github.com/huiyegit/MatchXML.