神经机器翻译模型,用于将爱沙尼亚语(et)翻译成英语(en)。
该模型是 OPUS-MT project 的一部分,旨在使神经机器翻译模型在世界上许多语言中广泛可用和易于访问。所有模型最初都是使用纯C++编写的高效NMT实现框架 Marian NMT 进行训练的。这些模型已经使用huggingface的transformers库转换为pyTorch。训练数据来自 OPUS 并且训练流程使用 OPUS-MT-train 的程序。
@inproceedings{tiedemann-thottingal-2020-opus, title = "{OPUS}-{MT} {--} Building open translation services for the World", author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh}, booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation", month = nov, year = "2020", address = "Lisboa, Portugal", publisher = "European Association for Machine Translation", url = "https://aclanthology.org/2020.eamt-1.61", pages = "479--480", } @inproceedings{tiedemann-2020-tatoeba, title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}", author = {Tiedemann, J{\"o}rg}, booktitle = "Proceedings of the Fifth Conference on Machine Translation", month = nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2020.wmt-1.139", pages = "1174--1182", }
简短的示例代码:
from transformers import MarianMTModel, MarianTokenizer src_text = [ "Takso ootab.", "Kon sa elät?" ] model_name = "pytorch-models/opus-mt-tc-big-et-en" tokenizer = MarianTokenizer.from_pretrained(model_name) model = MarianMTModel.from_pretrained(model_name) translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True)) for t in translated: print( tokenizer.decode(t, skip_special_tokens=True) ) # expected output: # Taxi's waiting. # Kon you elät?
您也可以使用transformers库的pipelines功能来使用OPUS-MT模型,例如:
from transformers import pipeline pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-et-en") print(pipe("Takso ootab.")) # expected output: Taxi's waiting.
langpair | testset | chr-F | BLEU | #sent | #words |
---|---|---|---|---|---|
est-eng | tatoeba-test-v2021-08-07 | 0.73707 | 59.7 | 1359 | 8811 |
est-eng | flores101-devtest | 0.64463 | 38.6 | 1012 | 24721 |
est-eng | newsdev2018 | 0.59899 | 33.8 | 2000 | 43068 |
est-eng | newstest2018 | 0.60708 | 34.3 | 2000 | 45405 |
该工作得到 European Language Grid 的支持,以及 pilot project 2866 提供的资源支持,该项目由欧洲研究理事会(ERC)根据欧洲联盟的Horizon 2020研究和创新计划(授权协议号771113)以及 FoTran project 和 MeMAD project 在欧洲联盟的Horizon 2020研究和创新计划(授权协议号780069)下资助。我们还感谢 CSC -- IT Center for Science 提供的慷慨计算资源和IT基础设施,芬兰。