paper-with-me

Papers

Contextualizing Hate Speech Classifiers with Post-hoc Explanation

2020-05-05 · ACL 2020 6 · Brendan Kennedy, Xisen Jin, Aida Mostafazadeh Davani, Morteza Dehghani, Xiang Ren

Hate speech classifiers trained on imbalanced datasets struggle to determine if group identifiers like "gay" or "black" are used in offensive or prejudiced ways. Such biases manifest in false positives when these identifiers are present, due to models' inability to learn the contexts which constitute a hateful usage of identifiers. We extract SOC post-hoc explanations from fine-tuned BERT classifiers to efficiently detect bias towards identity terms. Then, we propose a novel regularization technique based on these explanations that encourages models to learn from the context of group identifiers in addition to the identifiers themselves. Our approach improved over baselines in limiting false positives on out-of-domain data while maintaining or improving in-domain performance. Project page: https://inklab.usc.edu/contextualize-hate-speech/.

📄 PDF Abstract BibTeX arXiv:2005.02439

Code (3)

BrendanKennedy/contextualizing-hate-speech-models-with-explanations 공식 구현 pytorch
Ago3/Adversifier
owaisCS/TestHateSpeech pytorch

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Reproducibility Report: Contextualizing Hate Speech Classifiers with Post-hoc Explanation

2021-05-24 · Kiran Purohit, Owais Iqbal, Ankan Mullick

The presented report evaluates Contextualizing Hate Speech Classifiers with Post-hoc Explanation paper within the scope of ML Reproducibility Challenge 2020. Our work focuses on both aspects constituting the paper: the m…

Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection

2022-05-01 · nlppower (ACL) 2022 5 · Giuseppe Attanasio, Debora Nozza, Eliana Pastor, Dirk Hovy

Transformer-based Natural Language Processing models have become the standard for hate speech detection. However, the unconscious use of these techniques for such a critical task comes with negative consequences. Various…

BenchmarkingHate Speech Detection

Explain the Flag: Contextualizing Hate Speech Beyond Censorship

2026-04-16 · Jason Liartis, Eirini Kaldeli, Lambrini Gyftokosta, Eleftherios Chelioudakis 외 arxiv

Hate, derogatory, and offensive speech remains a persistent challenge in online platforms and public discourse. While automated detection systems are widely used, most focus on censorship or removal, raising concerns for…

Hate Speech Detection

Aligning Attention with Human Rationales for Self-Explaining Hate Speech Detection

2025-11-10 · Brage Eilertsen, Røskva Bjørgfinsdóttir, Francielle Vargas, Ali Ramezani-Kebrya arxiv

The opaque nature of deep learning models presents significant challenges for the ethical deployment of hate speech detection systems. To address this limitation, we introduce Supervised Rational Attention (SRA), a frame…

Hate Speech Detection

Contextualizing Internet Memes Across Social Media Platforms

2023-11-18 · Saurav Joshi, Filip Ilievski, Luca Luceri

Internet memes have emerged as a novel format for communication and expressing ideas on the web. Their fluidity and creative nature are reflected in their widespread use, often across platforms and occasionally for uneth…

Hate Speech Detection