Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model

Abstract

Because it is not feasible to collect training data for every language, there is a growing interest in cross-lingual transfer learning. In this paper, we systematically explore zero-shot cross-lingual transfer learning on reading comprehension tasks with a language representation model pre-trained on multi-lingual corpus. The experimental results show that with pre-trained language representation zero-shot learning is feasible, and translating the source data into the target language is not necessary and even degrades the performance. We further explore what does the model learn in zero-shot setting.

References in corpus (1)

• Cross-lingual Language Model Pretraining

Cited by in corpus (9)

• A Call for More Rigor in Unsupervised Cross-lingual Learning
• A Study of Cross-Lingual Ability and Language-specific Information in Multilingual BERT
• What makes multilingual BERT multilingual?
• Zero-Shot Cross-Lingual Dependency Parsing through Contextual Embedding Transformation
• Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation
• Looking for Clues of Language in Multilingual BERT to Improve Cross-lingual Generalization
• Improving Cross-Lingual Reading Comprehension with Self-Training
• A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters
• The Effectiveness of Intermediate-Task Training for Code-Switched Natural Language Understanding