Roberta Base Wechsel Swahili

🚀 roberta-base-wechsel-swahili

該模型使用WECHSEL進行訓練，可有效初始化子詞嵌入，用於單語言模型的跨語言遷移。

查看代碼請訪問：https://github.com/CPJKU/wechsel

查看論文請訪問：https://aclanthology.org/2022.naacl-main.293/

✨ 主要特性

該模型藉助WECHSEL方法，能高效且有效地將預訓練語言模型遷移到新的語言上，尤其在跨語言參數遷移方面表現出色，相比從頭開始訓練的同等規模模型，能以低至1/64的訓練成本取得更優效果。

📚 詳細文檔

性能表現

RoBERTa模型

GPT2模型

更多詳細信息請參考我們的論文。

📄 許可證

本項目採用MIT許可證。

📚 引用信息

如果您使用了本模型或相關研究，請引用以下論文：

@inproceedings{minixhofer-etal-2022-wechsel,
    title = "{WECHSEL}: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models",
    author = "Minixhofer, Benjamin  and
      Paischer, Fabian  and
      Rekabsaz, Navid",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.naacl-main.293",
    pages = "3992--4006",
    abstract = "Large pretrained language models (LMs) have become the central building block of many NLP applications. Training these models requires ever more computational resources and most of the existing models are trained on English text only. It is exceedingly expensive to train these models in other languages. To alleviate this problem, we introduce a novel method {--} called WECHSEL {--} to efficiently and effectively transfer pretrained LMs to new languages. WECHSEL can be applied to any model which uses subword-based tokenization and learns an embedding for each subword. The tokenizer of the source model (in English) is replaced with a tokenizer in the target language and token embeddings are initialized such that they are semantically similar to the English tokens by utilizing multilingual static word embeddings covering English and the target language. We use WECHSEL to transfer the English RoBERTa and GPT-2 models to four languages (French, German, Chinese and Swahili). We also study the benefits of our method on very low-resource languages. WECHSEL improves over proposed methods for cross-lingual parameter transfer and outperforms models of comparable size trained from scratch with up to 64x less training effort. Our method makes training large language models for new languages more accessible and less damaging to the environment. We make our code and models publicly available.",
}