arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.09368cs.CL
收藏

第一个Erzya语言的神经机器翻译系统

The first neural machine translation system for the Erzya language

Skolkovo Institute of Science and Technology (Skoltech)(斯科尔科沃科学技术研究院(Skoltech));Meta AI

David Dale

摘要:

我们提出了第一个神经机器翻译系统,用于濒危的Erzya语和俄语之间的翻译,以及我们收集的数据集进行训练和评估。BLEU分数分别为17和19,翻译成Erzya语和俄语,超过一半的翻译被母语人士评为可接受。我们还调整了我们的模型,以在Erzya和其他10种语言之间进行翻译,但如果没有额外的并行数据,这些方向的质量仍然很低。我们发布了翻译模型以及收集的文本语料库、新的语言识别模型和适用于Erzya语言的多语言句子编码器。这些资源将在https://github.com/slone-nlp/myv-nmt上提供。

英文摘要:

We present the first neural machine translation system for translation between the endangered Erzya language and Russian and the dataset collected by us to train and evaluate it. The BLEU scores are 17 and 19 for translation to Erzya and Russian respectively, and more than half of the translations are rated as acceptable by native speakers. We also adapt our model to translate between Erzya and 10 other languages, but without additional parallel data, the quality on these directions remains low. We release the translation models along with the collected text corpus, a new language identification model, and a multilingual sentence encoder adapted for the Erzya language. These resources will be available at https://github.com/slone-nlp/myv-nmt.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑