神经机器翻译模型,用于将土耳其语(tr)翻译成英语(en)。
此模型是 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可访问。所有模型最初使用 Marian NMT 的优秀框架进行训练,这是一个用纯 C++ 编写的高效 NMT 实现。使用 transformers 库和 huggingface 将模型转换为 pyTorch。训练数据取自 OPUS ,并使用 OPUS-MT-train 的流程进行训练。
@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 = [ "Allahsızlığı Yayma Kürsüsü başkanıydı.", "Tom'a ne olduğunu öğrenin." ] model_name = "pytorch-models/opus-mt-tc-big-tr-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: # He was the president of the Curse of Spreading Godlessness. # Find out what happened to Tom.
您还可以使用 transformers pipelines 使用 OPUS-MT 模型,例如:
from transformers import pipeline pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-tr-en") print(pipe("Allahsızlığı Yayma Kürsüsü başkanıydı.")) # expected output: He was the president of the Curse of Spreading Godlessness.
langpair | testset | chr-F | BLEU | #sent | #words |
---|---|---|---|---|---|
tur-eng | tatoeba-test-v2021-08-07 | 0.71895 | 57.6 | 13907 | 109231 |
tur-eng | flores101-devtest | 0.64152 | 37.6 | 1012 | 24721 |
tur-eng | newsdev2016 | 0.58658 | 32.1 | 1001 | 21988 |
tur-eng | newstest2016 | 0.56960 | 29.3 | 3000 | 66175 |
tur-eng | newstest2017 | 0.57455 | 29.7 | 3007 | 67703 |
tur-eng | newstest2018 | 0.58488 | 30.7 | 3000 | 68725 |
该工作得到 European Language Grid 的支持,作为 pilot project 2866 ,以及 FoTran project 的支持,该项目由欧洲研究委员会(ERC)在欧洲联盟的Horizon 2020研究和创新计划(授权协议编号:771113)下资助,以及 MeMAD project 的支持,该项目在欧洲联盟的Horizon 2020研究和创新计划下获得资助,授权协议编号:780069。我们还对芬兰的 CSC -- IT Center for Science 提供的慷慨计算资源和IT基础设施表示感谢。