Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?

TL;DR

This survey reviews existing NLU benchmarks with diagnostics datasets across multiple languages, highlighting the lack of standardization in linguistic phenomena categorization and evaluation metrics, and advocates for unified diagnostics standards.

Contribution

It provides a comprehensive comparison of NLU benchmarks, identifies gaps in linguistic phenomena coverage, and proposes the development of standardized evaluation metrics and categories.

Findings

No standard naming convention for linguistic categories.

Lack of a unified set of linguistic phenomena in benchmarks.

Potential benefits of standardized diagnostics metrics.

Abstract

Natural Language Understanding (NLU) is a basic task in Natural Language Processing (NLP). The evaluation of NLU capabilities has become a trending research topic that attracts researchers in the last few years, resulting in the development of numerous benchmarks. These benchmarks include various tasks and datasets in order to evaluate the results of pretrained models via public leaderboards. Notably, several benchmarks contain diagnostics datasets designed for investigation and fine-grained error analysis across a wide range of linguistic phenomena. This survey provides a comprehensive review of available English, Arabic, and Multilingual NLU benchmarks, with a particular emphasis on their diagnostics datasets and the linguistic phenomena they covered. We present a detailed comparison and analysis of these benchmarks, highlighting their strengths and limitations in evaluating NLU tasks and providing in-depth error analysis. When highlighting the gaps in the state-of-the-art, we noted that there is no naming convention for macro and micro categories or even a standard set of linguistic phenomena that should be covered. Consequently, we formulated a research question regarding the evaluation metrics of the evaluation diagnostics benchmarks: "Why do not we have an evaluation standard for the NLU evaluation diagnostics benchmarks?" similar to ISO standard in industry. We conducted a deep analysis and comparisons of the covered linguistic phenomena in order to support experts in building a global hierarchy for linguistic phenomena in future. We think that having evaluation metrics for diagnostics evaluation could be valuable to gain more insights when comparing the results of the studied models on different diagnostics benchmarks.