wechsel

韦希塞尔

Wechsel的代码：在NAACL2022上发表的单语言模型的跨语言转移的子词嵌入的有效初始化。

论文：https：//aclanthology.org/2022.naacl-main.293/

纸上的模型可在Huggingface Hub上使用：

• roberta-base-wechsel-french
• roberta-base-wechsel-german
• roberta-base-wechsel-chinese
• roberta-base-wechsel-swahili
• gpt2-wechsel-french
• gpt2-wechsel-german
• gpt2-wechsel-chinese
• gpt2-wechsel-swahili

安装

我们通过PYPI分发Python包：

 pip install wechsel

另外，请克隆存储库，安装requirements.txt并在wechsel/中运行代码。

示例用法

将英语roberta-base转移到斯瓦希里语：

 import torch
from transformers import AutoModel , AutoTokenizer
from datasets import load_dataset
from wechsel import WECHSEL , load_embeddings

source_tokenizer = AutoTokenizer . from_pretrained ( "roberta-base" )
model = AutoModel . from_pretrained ( "roberta-base" )

target_tokenizer = source_tokenizer . train_new_from_iterator (
    load_dataset ( "oscar" , "unshuffled_deduplicated_sw" , split = "train" )[ "text" ],
    vocab_size = len ( source_tokenizer )
)

wechsel = WECHSEL (
    load_embeddings ( "en" ),
    load_embeddings ( "sw" ),
    bilingual_dictionary = "swahili"
)

target_embeddings , info = wechsel . apply (
    source_tokenizer ,
    target_tokenizer ,
    model . get_input_embeddings (). weight . detach (). numpy (),
)

model . get_input_embeddings (). weight . data = torch . from_numpy ( target_embeddings )
model . config . vocab_size = len ( target_embeddings )

# if the model has separate output embeddings, also copy those
if not model . config . tie_word_embeddings :
    target_out_embeddings , info = wechsel . apply (
        source_tokenizer ,
        target_tokenizer ,
        model . get_output_embeddings (). weight . detach (). numpy (),
    )
    model . get_output_embeddings (). weight . data = torch . from_numpy ( target_out_embeddings )

# use `model` and `target_tokenizer` to continue training in Swahili! 

双语词典

我们将3276个双语词典从英语分发到其他语言，以与dicts/一起使用。

引用

请引用韦切塞尔

 @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.",
}

致谢

Google TPU研究云（TRC）的Cloud TPU支持研究。我们感谢Andy Koh和Artus Krohn-Grimberghe提供了其他计算资源。 Ellis Unit Linz，LIT AI实验室，机器学习研究所，由联邦州立Upper Austria支持。我们感谢该项目Incontrol-RL（FFG-881064）。