paper-with-me

홈 › Papers

Reducing Unintended Identity Bias in Russian Hate Speech Detection

2020-10-22 · EMNLP (ALW) 2020 11 · Nadezhda Zueva, Madina Kabirova, Pavel Kalaidin

Toxicity has become a grave problem for many online communities and has been growing across many languages, including Russian. Hate speech creates an environment of intimidation, discrimination, and may even incite some real-world violence. Both researchers and social platforms have been focused on developing models to detect toxicity in online communication for a while now. A common problem of these models is the presence of bias towards some words (e.g. woman, black, jew) that are not toxic, but serve as triggers for the classifier due to model caveats. In this paper, we describe our efforts towards classifying hate speech in Russian, and propose simple techniques of reducing unintended bias, such as generating training data with language models using terms and words related to protected identities as context and applying word dropout to such words.

📄 PDF Abstract BibTeX arXiv:2010.11666

Code (0)

등록된 구현이 없습니다.

Tasks

Hate Speech Detection

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists

2022-03-17 · Findings (ACL) 2022 5 · Giuseppe Attanasio, Debora Nozza, Dirk Hovy, Elena Baralis

Natural Language Processing (NLP) models risk overfitting to specific terms in the training data, thereby reducing their performance, fairness, and generalizability. E.g., neural hate speech detection models are strongly…

Abuse DetectionBias DetectionFairnessHate Speech Detection

Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech Detection

2022-05-09 · NAACL 2022 7 · Indira Sen, Mattia Samory, Claudia Wagner, Isabelle Augenstein

Counterfactually Augmented Data (CAD) aims to improve out-of-domain generalizability, an indicator of model robustness. The improvement is credited with promoting core features of the construct over spurious artifacts th…

Hate Speech Detection

Perturbation Sensitivity Analysis to Detect Unintended Model Biases

2019-10-09 · IJCNLP 2019 11 · Vinodkumar Prabhakaran, Ben Hutchinson, Margaret Mitchell

Data-driven statistical Natural Language Processing (NLP) techniques leverage large amounts of language data to build models that can understand language. However, most language data reflect the public discourse at the t…

modelSensitivitySentiment Analysis

HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection

2020-12-18 · Binny Mathew, Punyajoy Saha, Seid Muhie Yimam, Chris Biemann 외

Hate speech is a challenging issue plaguing the online social media. While better models for hate speech detection are continuously being developed, there is little research on the bias and interpretability aspects of ha…

Hate Speech DetectionText Classification

Detecting Unintended Social Bias in Toxic Language Datasets

2022-10-21 · Nihar Sahoo, Himanshu Gupta, Pushpak Bhattacharyya

With the rise of online hate speech, automatic detection of Hate Speech, Offensive texts as a natural language processing task is getting popular. However, very little research has been done to detect unintended social b…