NLPre: a revised approach towards language-centric benchmarking of Natural Language Preprocessing systems

TL;DR

NLPre introduces a language-centric benchmarking system inspired by GLUE, enabling fair, comprehensive evaluation of NLP preprocessing tools across multiple languages, demonstrated through Polish and adaptable for others.

Contribution

It proposes a novel, fair evaluation framework for NLP preprocessing tools, addressing limitations of existing methods and providing a customizable, language-agnostic benchmarking system.

Findings

Extensive evaluation of Polish NLPre tools using the benchmark.

Demonstrated the system's adaptability for other languages like Irish and Chinese.

Provided publicly available resources for benchmarking and tool evaluation.

Abstract

With the advancements of transformer-based architectures, we observe the rise of natural language preprocessing (NLPre) tools capable of solving preliminary NLP tasks (e.g. tokenisation, part-of-speech tagging, dependency parsing, or morphological analysis) without any external linguistic guidance. It is arduous to compare novel solutions to well-entrenched preprocessing toolkits, relying on rule-based morphological analysers or dictionaries. Aware of the shortcomings of existing NLPre evaluation approaches, we investigate a novel method of reliable and fair evaluation and performance reporting. Inspired by the GLUE benchmark, the proposed language-centric benchmarking system enables comprehensive ongoing evaluation of multiple NLPre tools, while credibly tracking their performance. The prototype application is configured for Polish and integrated with the thoroughly assembled NLPre-PL benchmark. Based on this benchmark, we conduct an extensive evaluation of a variety of Polish NLPre systems. To facilitate the construction of benchmarking environments for other languages, e.g. NLPre-GA for Irish or NLPre-ZH for Chinese, we ensure full customization of the publicly released source code of the benchmarking system. The links to all the resources (deployed platforms, source code, trained models, datasets etc.) can be found on the project website: https://sites.google.com/view/nlpre-benchmark.