Roberta Base Wechsel Swahili

🚀 roberta-base-wechsel-swahili

A model trained with WECHSEL, which enables effective initialization of subword embeddings for cross - lingual transfer of monolingual language models.

See the code here: https://github.com/CPJKU/wechsel

And the paper here: https://aclanthology.org/2022.naacl-main.293/

🚀 Quick Start

This section provides an overview of the roberta - base - wechsel - swahili model, its performance, and citation information. For more details, please refer to the corresponding links and the paper.

✨ Features

The roberta - base - wechsel - swahili model is trained using the WECHSEL method, which effectively initializes sub - word embeddings for cross - lingual transfer of monolingual language models. This approach allows for more efficient and effective adaptation of pre - trained language models to new languages.

📚 Documentation

Performance

RoBERTa

GPT2

See our paper for details.

📄 License

This project is licensed under the MIT license.

📚 Citation

Please cite WECHSEL as

@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.",
}