论文标题
Slovene Superglue基准：翻译和评估
Slovene SuperGLUE Benchmark: Translation and Evaluation
论文作者
论文摘要
我们提出了一个斯洛文尼式合并的机器人翻译的超级亮度基准。我们描述了由于形态和语法差异而引起的翻译过程和问题。我们以几种模式评估了翻译的数据集：单语言，跨语义和多语言，考虑到机器和人类翻译训练集之间的差异。结果表明，单语的Slovene Sloberta模型优于大量多语言和三语BERT模型，但这些模型在某些任务上也表现出良好的跨语性性能。斯洛文尼型模型的性能仍然落后于最好的英语型号。
We present a Slovene combined machine-human translated SuperGLUE benchmark. We describe the translation process and problems arising due to differences in morphology and grammar. We evaluate the translated datasets in several modes: monolingual, cross-lingual, and multilingual, taking into account differences between machine and human translated training sets. The results show that the monolingual Slovene SloBERTa model is superior to massively multilingual and trilingual BERT models, but these also show a good cross-lingual performance on certain tasks. The performance of Slovene models still lags behind the best English models.
