RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark
This addresses the need for broad diagnostics of language models in Russian, offering a tool for researchers and practitioners in NLP, though it is incremental as it adapts an existing methodology to a new language.
The authors introduced RussianSuperGLUE, a benchmark of nine tasks for evaluating Russian language understanding, developed from scratch analogously to SuperGLUE, and provided baselines, human-level evaluations, and an open-source framework.
In this paper, we introduce an advanced Russian general language understanding evaluation benchmark -- RussianGLUE. Recent advances in the field of universal language models and transformers require the development of a methodology for their broad diagnostics and testing for general intellectual skills - detection of natural language inference, commonsense reasoning, ability to perform simple logical operations regardless of text subject or lexicon. For the first time, a benchmark of nine tasks, collected and organized analogically to the SuperGLUE methodology, was developed from scratch for the Russian language. We provide baselines, human level evaluation, an open-source framework for evaluating models (https://github.com/RussianNLP/RussianSuperGLUE), and an overall leaderboard of transformer models for the Russian language. Besides, we present the first results of comparing multilingual models in the adapted diagnostic test set and offer the first steps to further expanding or assessing state-of-the-art models independently of language.