SGHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Singapore

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ng, Ri Chi, Prakash, Nirmalendu, Hee, Ming Shan, Choo, Kenny Tsu Wei, Lee, Roy Ka-Wei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917656300355584
author Ng, Ri Chi
Prakash, Nirmalendu
Hee, Ming Shan
Choo, Kenny Tsu Wei
Lee, Roy Ka-Wei
author_facet Ng, Ri Chi
Prakash, Nirmalendu
Hee, Ming Shan
Choo, Kenny Tsu Wei
Lee, Roy Ka-Wei
contents To address the limitations of current hate speech detection models, we introduce \textsf{SGHateCheck}, a novel framework designed for the linguistic and cultural context of Singapore and Southeast Asia. It extends the functional testing approach of HateCheck and MHC, employing large language models for translation and paraphrasing into Singapore's main languages, and refining these with native annotators. \textsf{SGHateCheck} reveals critical flaws in state-of-the-art models, highlighting their inadequacy in sensitive content moderation. This work aims to foster the development of more effective hate speech detection tools for diverse linguistic environments, particularly for Singapore and Southeast Asia contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2405_01842
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SGHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Singapore
Ng, Ri Chi
Prakash, Nirmalendu
Hee, Ming Shan
Choo, Kenny Tsu Wei
Lee, Roy Ka-Wei
Computation and Language
To address the limitations of current hate speech detection models, we introduce \textsf{SGHateCheck}, a novel framework designed for the linguistic and cultural context of Singapore and Southeast Asia. It extends the functional testing approach of HateCheck and MHC, employing large language models for translation and paraphrasing into Singapore's main languages, and refining these with native annotators. \textsf{SGHateCheck} reveals critical flaws in state-of-the-art models, highlighting their inadequacy in sensitive content moderation. This work aims to foster the development of more effective hate speech detection tools for diverse linguistic environments, particularly for Singapore and Southeast Asia contexts.
title SGHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Singapore
topic Computation and Language
url https://arxiv.org/abs/2405.01842