AustroTox: A Dataset for Target-Based Austrian German Offensive Language Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pachinger, Pia, Goldzycher, Janis, Planitzer, Anna Maria, Kusa, Wojciech, Hanbury, Allan, Neidhardt, Julia
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929383003914240
author Pachinger, Pia
Goldzycher, Janis
Planitzer, Anna Maria
Kusa, Wojciech
Hanbury, Allan
Neidhardt, Julia
author_facet Pachinger, Pia
Goldzycher, Janis
Planitzer, Anna Maria
Kusa, Wojciech
Hanbury, Allan
Neidhardt, Julia
contents Model interpretability in toxicity detection greatly profits from token-level annotations. However, currently such annotations are only available in English. We introduce a dataset annotated for offensive language detection sourced from a news forum, notable for its incorporation of the Austrian German dialect, comprising 4,562 user comments. In addition to binary offensiveness classification, we identify spans within each comment constituting vulgar language or representing targets of offensive statements. We evaluate fine-tuned language models as well as large language models in a zero- and few-shot fashion. The results indicate that while fine-tuned models excel in detecting linguistic peculiarities such as vulgar dialect, large language models demonstrate superior performance in detecting offensiveness in AustroTox. We publish the data and code.
format Preprint
id arxiv_https___arxiv_org_abs_2406_08080
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AustroTox: A Dataset for Target-Based Austrian German Offensive Language Detection
Pachinger, Pia
Goldzycher, Janis
Planitzer, Anna Maria
Kusa, Wojciech
Hanbury, Allan
Neidhardt, Julia
Computation and Language
Artificial Intelligence
Computers and Society
I.2.7
Model interpretability in toxicity detection greatly profits from token-level annotations. However, currently such annotations are only available in English. We introduce a dataset annotated for offensive language detection sourced from a news forum, notable for its incorporation of the Austrian German dialect, comprising 4,562 user comments. In addition to binary offensiveness classification, we identify spans within each comment constituting vulgar language or representing targets of offensive statements. We evaluate fine-tuned language models as well as large language models in a zero- and few-shot fashion. The results indicate that while fine-tuned models excel in detecting linguistic peculiarities such as vulgar dialect, large language models demonstrate superior performance in detecting offensiveness in AustroTox. We publish the data and code.
title AustroTox: A Dataset for Target-Based Austrian German Offensive Language Detection
topic Computation and Language
Artificial Intelligence
Computers and Society
I.2.7
url https://arxiv.org/abs/2406.08080