UniPSDA: Unsupervised Pseudo Semantic Data Augmentation for Zero-Shot Cross-Lingual Natural Language Understanding

Dongyang Li, Taolin Zhang, Jiali Deng, Longtao Huang, Chengyu Wang, Xiaofeng He, Hui Xue


Abstract
Cross-lingual representation learning transfers knowledge from resource-rich data to resource-scarce ones to improve the semantic understanding abilities of different languages. However, previous works rely on shallow unsupervised data generated by token surface matching, regardless of the global context-aware semantics of the surrounding text tokens. In this paper, we propose an Unsupervised Pseudo Semantic Data Augmentation (UniPSDA) mechanism for cross-lingual natural language understanding to enrich the training data without human interventions. Specifically, to retrieve the tokens with similar meanings for the semantic data augmentation across different languages, we propose a sequential clustering process in 3 stages: within a single language, across multiple languages of a language family, and across languages from multiple language families. Meanwhile, considering the multi-lingual knowledge infusion with context-aware semantics while alleviating computation burden, we directly replace the key constituents of the sentences with the above-learned multi-lingual family knowledge, viewed as pseudo-semantic. The infusion process is further optimized via three de-biasing techniques without introducing any neural parameters. Extensive experiments demonstrate that our model consistently improves the performance on general zero-shot cross-lingual natural language understanding tasks, including sequence classification, information extraction, and question answering.
Anthology ID:
2024.lrec-main.1482
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
17062–17073
Language:
URL:
https://aclanthology.org/2024.lrec-main.1482
DOI:
Bibkey:
Cite (ACL):
Dongyang Li, Taolin Zhang, Jiali Deng, Longtao Huang, Chengyu Wang, Xiaofeng He, and Hui Xue. 2024. UniPSDA: Unsupervised Pseudo Semantic Data Augmentation for Zero-Shot Cross-Lingual Natural Language Understanding. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 17062–17073, Torino, Italia. ELRA and ICCL.
Cite (Informal):
UniPSDA: Unsupervised Pseudo Semantic Data Augmentation for Zero-Shot Cross-Lingual Natural Language Understanding (Li et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2024.lrec-main.1482.pdf