Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model
Journal
EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference
Pages
5933-5940
Date Issued
2020
Author(s)
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 setting0. © 2019 Association for Computational Linguistics
Other Subjects
Learning systems; Linguistics; Natural language processing systems; Cross-lingual; Reading comprehension; Representation model; Source data; Target language; Training data; Transfer learning
Type
conference paper