Checking HateCheck: a cross-functional analysis of behaviour-aware learning for hate speech detection

Checking HateCheck: a cross-functional analysis of behaviour-aware learning for hate speech detection

Abstract

Behavioural testing—-verifying system capabilities by validating human-designed input-output pairs—-is an alternative evaluation method of natural language processing systems proposed to address the shortcomings of the standard approach: computing metrics on held-out data. While behavioural tests capture human prior knowledge and insights, there has been little exploration on how to leverage them for model training and development. With this in mind, we explore behaviour-aware learning by examining several fine-tuning schemes using HateCheck, a suite of functional tests for hate speech detection systems. To address potential pitfalls of training on data originally intended for evaluation, we train and evaluate models on different configurations of HateCheck by holding out categories of test cases, which enables us to estimate performance on potentially overlooked system properties. The fine-tuning procedure led to improvements in the classification accuracy of held-out functionalities and identity groups, suggesting that models can potentially generalise to overlooked functionalities. However, performance on held-out functionality classes and i.i.d. hate speech detection data decreased, which indicates that generalisation occurs mostly across functionalities from the same class and that the procedure led to overfitting to the HateCheck data distribution.

Grafik Top
Authors
  • Luz de Araujo, Pedro Henrique
  • Roth, Benjamin
Grafik Top
Shortfacts
Category
Paper in Conference Proceedings or in Workshop Proceedings (Paper)
Event Title
NLP Power! The First Workshop on Efficient Benchmarking in NLP
Divisions
Data Mining and Machine Learning
Subjects
Kuenstliche Intelligenz
Event Location
Dublin, Ireland
Event Type
Workshop
Event Dates
26 May 2022
Series Name
Proceedings of NLP Power! The First Workshop on Efficient Benchmarking in NLP
Publisher
Association for Computational Linguistics
Page Range
pp. 75-83
Date
May 2022
Official URL
https://aclanthology.org/2022.nlppower-1.8
Export
Grafik Top