Options
Investigating transfer learning in multilingual pre-trained language models through Chinese natural language inference
Date Issued
2021
Publisher
Association for Computational Linguistics
Conference
Citation
Hu, H., etal. (2021). Investigating transfer learning in multilingual pre-trained language models through Chinese natural language inference. In Zong, C., Xia, F., Li, W., & Navigli, R. (Eds.). Findings of the association for computational linguistics: ACL-IJCNLP 2021, Berkeley Hotel in Bangkok, Thailand (pp. 3770-3785). Association for Computational Linguistics.
Description
Open access
Type
Conference Paper
Abstract
Multilingual transformers (XLM, mT5) have been shown to have remarkable transfer skills in zero-shot settings. Most transfer studies, however, rely on automatically translated resources (XNLI, XQuAD), making it hard to discern the particular linguistic knowledge that is being transferred, and the role of expert annotated monolingual datasets when developing task-specific models. We investigate the cross-lingual transfer abilities of XLM-R for Chinese and English natural language inference (NLI), with a focus on the recent largescale Chinese dataset OCNLI. To better understand linguistic transfer, we created 4 categories of challenge and adversarial tasks (totaling 17 new datasets1) for Chinese that build on several well-known resources for English (e.g., HANS, NLI stress-tests). We find that cross-lingual models trained on English NLI do transfer well across our Chinese tasks (e.g., in 3/4 of our challenge categories, they perform as well/better than the best monolingual models, even on 3/5 uniquely Chinese linguistic phenomena such as idioms, pro drop). These results, however, come with important caveats: cross-lingual models often perform best when trained on a mixture of English and high-quality monolingual NLI data (OCNLI), and are often hindered by automatically translated resources (XNLI-zh). For many phenomena, all models continue to struggle, highlighting the need for our new diagnostics to help benchmark Chinese and cross-lingual models.
Availability at HKSYU Library
