Cross-lingual Text Classification with Heterogeneous Graph Neural Network

Ziyun Wang, Xuan Liu, Peiji Yang, Shixing Liu, Zhisheng Wang


Abstract
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.
Anthology ID:
2021.acl-short.78
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
612–620
Language:
URL:
https://aclanthology.org/2021.acl-short.78
DOI:
10.18653/v1/2021.acl-short.78
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.78.pdf
Code
 TencentGameMate/gnn_cross_lingual
Data
XGLUE