The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics

TL;DR

GEM is a comprehensive, evolving benchmark for natural language generation that aims to standardize evaluation across diverse tasks, languages, and metrics, facilitating progress in the field.

Contribution

It introduces a living benchmark platform for NLG that supports diverse tasks, multilingual evaluation, and regular updates to improve model assessment.

Findings

Provides a unified environment for NLG evaluation

Supports multilingual and multi-task benchmarking

Encourages community participation and continuous improvement

Abstract

We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of automated metrics, datasets, and human evaluation standards. Due to this moving target, new models often still evaluate on divergent anglo-centric corpora with well-established, but flawed, metrics. This disconnect makes it challenging to identify the limitations of current models and opportunities for progress. Addressing this limitation, GEM provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested. Regular updates to the benchmark will help NLG research become more multilingual and evolve the challenge alongside models. This paper serves as the description of the data for which we are organizing a shared task at our ACL 2021 Workshop and to which we invite the entire NLG community to participate.