Xlm Align Base

🚀 XLM-Align

XLM-Align（ACL 2021，論文，倉庫，模型）通過自標註詞對齊改進預訓練跨語言語言模型。

XLM-Align 是一個支持 94 種語言的預訓練跨語言語言模型。更多詳情請參閱我們的論文。

🚀 快速開始

模型加載示例

model = AutoModel.from_pretrained("microsoft/xlm-align-base")

📊 評估結果

XTREME 跨語言理解任務

📄 MD5 信息

b9d214025837250ede2f69c9385f812c  config.json
6005db708eb4bab5b85fa3976b9db85b  pytorch_model.bin
bf25eb5120ad92ef5c7d8596b5dc4046  sentencepiece.bpe.model
eedbd60a7268b9fc45981b849664f747  tokenizer.json

📞 關於

聯繫方式

chizewen@outlook.com

BibTeX 引用

@inproceedings{xlmalign,
  title = "Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment",
  author={Zewen Chi and Li Dong and Bo Zheng and Shaohan Huang and Xian-Ling Mao and Heyan Huang and Furu Wei},
  booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
  month = aug,
  year = "2021",
  address = "Online",
  publisher = "Association for Computational Linguistics",
  url = "https://aclanthology.org/2021.acl-long.265",
  doi = "10.18653/v1/2021.acl-long.265",
  pages = "3418--3430",}