VALUE: Understanding Dialect Disparity in NLU

TL;DR

This paper introduces the VALUE benchmark to evaluate and understand dialect disparities in NLU systems, highlighting performance drops on African American Vernacular English (AAVE) and promoting more equitable language understanding.

Contribution

It creates a dialect-specific benchmark with transformation rules for AAVE, enabling analysis of biases and disparities in current NLU models.

Findings

Dialectal features cause performance drops in models

Participatory validation ensures linguistic accuracy

Benchmark facilitates development of dialect-robust NLU systems

Abstract

English Natural Language Understanding (NLU) systems have achieved great performances and even outperformed humans on benchmarks like GLUE and SuperGLUE. However, these benchmarks contain only textbook Standard American English (SAE). Other dialects have been largely overlooked in the NLP community. This leads to biased and inequitable NLU systems that serve only a sub-population of speakers. To understand disparities in current models and to facilitate more dialect-competent NLU systems, we introduce the VernAcular Language Understanding Evaluation (VALUE) benchmark, a challenging variant of GLUE that we created with a set of lexical and morphosyntactic transformation rules. In this initial release (V.1), we construct rules for 11 features of African American Vernacular English (AAVE), and we recruit fluent AAVE speakers to validate each feature transformation via linguistic acceptability judgments in a participatory design manner. Experiments show that these new dialectal features can lead to a drop in model performance. To run the transformation code and download both synthetic and gold-standard dialectal GLUE benchmarks, see https://github.com/SALT-NLP/value