Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection

Abstract

Hate speech classifiers exhibit substantial performance degradation when evaluated on datasets different from the source. This is due to learning spurious correlations between words that are not necessarily relevant to hateful language, and hate speech labels from the training corpus. Previous work has attempted to mitigate this problem by regularizing specific terms from pre-defined static dictionaries. While this has been demonstrated to improve the generalizability of classifiers, the coverage of such methods is limited and the dictionaries require regular manual updates from human experts. In this paper, we propose to automatically identify and reduce spurious correlations using attribution methods with dynamic refinement of the list of terms that need to be regularized during training. Our approach is flexible and improves the cross-corpora performance over previous work independently and in combination with pre-defined dictionaries.
Fichier principal
Vignette du fichier
ACL2022_Dyn_Ref_Tulika_Tracking-5.pdf (351.32 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03690174 , version 1 (07-06-2022)

Identifiers

Cite

Tulika Bose, Nikolaos Aletras, Irina Illina, Dominique Fohr. Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection. ACL 2022 - 60th meeting Association for Computational Linguistics Findings, May 2022, Dublin, Ireland. ⟨10.18653/v1/2022.findings-acl.32⟩. ⟨hal-03690174⟩
50 View
66 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More