This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish

TL;DR

This paper introduces LEPISZCZE, a comprehensive and flexible benchmark for Polish NLP, addressing the gap in standardized evaluation tools for low-resource languages and providing a blueprint for similar efforts.

Contribution

The paper presents LEPISZCZE, a new extensive benchmark for Polish NLP, including design principles, dataset integration, and initial experimental results, serving as a model for other low-resource languages.

Findings

LEPISZCZE includes 13 experiments with recent Polish language models.

The benchmark incorporates five existing and eight novel datasets.

Insights from creating LEPISZCZE can guide similar benchmarks for other languages.

Abstract

The availability of compute and data to train larger and larger language models increases the demand for robust methods of benchmarking the true progress of LM training. Recent years witnessed significant progress in standardized benchmarking for English. Benchmarks such as GLUE, SuperGLUE, or KILT have become de facto standard tools to compare large language models. Following the trend to replicate GLUE for other languages, the KLEJ benchmark has been released for Polish. In this paper, we evaluate the progress in benchmarking for low-resourced languages. We note that only a handful of languages have such comprehensive benchmarks. We also note the gap in the number of tasks being evaluated by benchmarks for resource-rich English/Chinese and the rest of the world. In this paper, we introduce LEPISZCZE (the Polish word for glew, the Middle English predecessor of glue), a new, comprehensive benchmark for Polish NLP with a large variety of tasks and high-quality operationalization of the benchmark. We design LEPISZCZE with flexibility in mind. Including new models, datasets, and tasks is as simple as possible while still offering data versioning and model tracking. In the first run of the benchmark, we test 13 experiments (task and dataset pairs) based on the five most recent LMs for Polish. We use five datasets from the Polish benchmark and add eight novel datasets. As the paper's main contribution, apart from LEPISZCZE, we provide insights and experiences learned while creating the benchmark for Polish as the blueprint to design similar benchmarks for other low-resourced languages.