Cross-lingual Text Classification with Heterogeneous Graph Neural Network
This addresses the problem of performance degradation in cross-lingual classification for low-resource languages, offering a novel approach beyond semantic similarity.
The paper tackled cross-lingual text classification by proposing a heterogeneous graph neural network method that incorporates factors like part-of-speech and translations, achieving significant performance gains over state-of-the-art models in all tasks and low-resource settings.
Cross-lingual text classification aims at training a classifier on the source language and transferring the knowledge to target languages, which is very useful for low-resource languages. Recent multilingual pretrained language models (mPLM) achieve impressive results in cross-lingual classification tasks, but rarely consider factors beyond semantic similarity, causing performance degradation between some language pairs. In this paper we propose a simple yet effective method to incorporate heterogeneous information within and across languages for cross-lingual text classification using graph convolutional networks (GCN). In particular, we construct a heterogeneous graph by treating documents and words as nodes, and linking nodes with different relations, which include part-of-speech roles, semantic similarity, and document translations. Extensive experiments show that our graph-based method significantly outperforms state-of-the-art models on all tasks, and also achieves consistent performance gain over baselines in low-resource settings where external tools like translators are unavailable.