We test similarity-based word alignment models (SimAlign and awesome-align)
in combination with word embeddings from mBERT and XLM-R on parallel sentences
in German and Romansh. Since Romansh is an unseen language, we are dealing with
a zero-shot setting. Using embeddings from mBERT, both models reach an
alignment error rate of 0.22, which outperforms fast_align, a statistical
model, and is on par with similarity-based word alignment for seen languages.
We interpret these results as evidence that mBERT contains information that can
be meaningful and applicable to Romansh.
To evaluate performance, we also present a new trilingual corpus, which we
call the DERMIT (DE-RM-IT) corpus, containing press releases made by the Canton
of Grisons in German, Romansh and Italian in the past 25 years. The corpus
contains 4 547 parallel documents and approximately 100 000 sentence pairs in
each language combination. We additionally present a gold standard for
German-Romansh word alignment. The data is available at
this https URL

我们测试了基于相似性的单词对齐模型（SimAlign 和 awesome-align）与来自 mBERT 和 XLM-R 的单词嵌入在德语和罗曼什语平行句子中的组合。通过使用来自 mBERT 的嵌入，两种模型都达到了 0.22 的对齐误差率，这优于基于快速对齐的统计模型，并且与已知语言的基于相似性的单词对齐持平。我们认为这些结果表明 mBERT 包含的信息可对罗曼什语具有意义且可应用。同时，我们还介绍了一种新的三语料库 DERMIT，其中包含德语，罗曼什语和意大利语的格里森州近 25 年来的新闻稿，该语料库包含 4,547 个平行文档和每种语言组合约 100,000 个句对。此外，我们还提供了德语 - 罗曼什语单词对齐的 “黄金标准”。