Zero-shot cross-lingual transfer language selection using linguistic similarity |
| |
| Institution: | 1. School of Information, Renmin University of China, Beijing 100872, PR China;2. School of Information Technology and Management, University of International Business and Economics, Beijing 100029, PR China;1. School of Information Management, Nanjing University, Nanjing 210023, China;2. School of International and Public Affairs, Shanghai Jiao Tong University, Shanghai 200230, China;1. School of Information Management and Artificial Intelligence, Zhejiang University of Finance and Economics, China;2. School of Economics and Management, Qilu University of Technology (Shandong Academy of Sciences), China;1. Faculty of Economics and Management, East China Normal University, Shanghai, China;2. Key Laboratory of Advanced Theory and Application in Statistics and Data Science (East China Normal University), Ministry of Education of China, Shanghai, China;3. University of Chinese Academy of Sciences, Shanghai, China;1. School of Cyber Science and Engineering, Sichuan University, Chengdu, China;2. Cybersecurity Research Institute, Sichuan University, Chengdu, China |
| |
| Abstract: | We study the selection of transfer languages for different Natural Language Processing tasks, specifically sentiment analysis, named entity recognition and dependency parsing. In order to select an optimal transfer language, we propose to utilize different linguistic similarity metrics to measure the distance between languages and make the choice of transfer language based on this information instead of relying on intuition. We demonstrate that linguistic similarity correlates with cross-lingual transfer performance for all of the proposed tasks. We also show that there is a statistically significant difference in choosing the optimal language as the transfer source instead of English. This allows us to select a more suitable transfer language which can be used to better leverage knowledge from high-resource languages in order to improve the performance of language applications lacking data. For the study, we used datasets from eight different languages from three language families. |
| |
| Keywords: | Multilingual natural language processing Zero-shot learning Transfer learning Linguistics Language similarity |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
