Crosslingual NLP

This repo supports various cross-lingual transfer learning & multilingual NLP models. It powers the following papars.

• Mahsa Yarmohammadi*, Shijie Wu*, Marc Marone, Haoran Xu, Seth Ebner, Guanghui Qin, Yunmo Chen, Jialiang Guo, Craig Harman, Kenton Murray, Aaron Steven White, Mark Dredze, and Benjamin Van Durme. Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction. EMNLP. 2021. (Experiments Detail)
• Shijie Wu and Mark Dredze. Do Explicit Alignments Robustly Improve Multilingual Encoders? EMNLP. 2020. (Experiments Detail)
• Shijie Wu and Mark Dredze. Are All Languages Created Equal in Multilingual BERT? RepL4NLP. 2020. (Experiments Detail)
• Shijie Wu*, Alexis Conneau*, Haoran Li, Luke Zettlemoyer, and Veselin Stoyanov. Emerging Cross-lingual Structure in Pretrained Language Models. ACL. 2020. (Experiments Detail)
• Shijie Wu and Mark Dredze. Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT. EMNLP. 2019. (Experiments Detail)

Miscellaneous

• Environment (conda): environment.yml
• Pre-commit check: pre-commit run --all-files

License

MIT