Related papers: Evaluating Simple Debiasing Techniques in RoBERTa-…
This paper investigates the transferability of debiasing techniques across different languages within multilingual models. We examine the applicability of these techniques in English, French, German, and Dutch. Using multilingual BERT…
Recent research in Natural Language Processing has revealed that word embeddings can encode social biases present in the training data which can affect minorities in real world applications. This paper explores the gender bias implicit in…
The dissemination of online hate speech can have serious negative consequences for individuals, online communities, and entire societies. This and the large volume of hateful online content prompted both practitioners', i.e., in content…
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 influenced by…
The widespread presence of hate speech on the internet, including formats such as text-based tweets and vision-language memes, poses a significant challenge to digital platform safety. Recent research has developed detection models tailored…
Existing approaches to mitigate demographic biases evaluate on monolingual data, however, multilingual data has not been examined. In this work, we treat the gender as domains (e.g., male vs. female) and present a standard domain adaptation…
The meteoric rise in text generation capability has been accompanied by parallel growth in interest in machine-generated text detection: the capability to identify whether a given text was generated using a model or written by a person.…
The pervasiveness of the Internet and social media have enabled the rapid and anonymous spread of Hate Speech content on microblogging platforms such as Twitter. Current EU and US legislation against hateful language, in conjunction with…
Social media platforms, while enabling global connectivity, have become hubs for the rapid spread of harmful content, including hate speech and fake narratives \cite{davidson2017automated, shu2017fake}. The Faux-Hate shared task focuses on…
Automatic Speech Recognition (ASR) systems have been examined and shown to exhibit biases toward particular groups of individuals, influenced by factors such as demographic traits, accents, and speech styles. Noise can disproportionately…
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,…
The objective of this study is to improve automated feedback tools designed for English Language Learners (ELLs) through the utilization of data science techniques encompassing machine learning, natural language processing, and educational…
The spread of hate speech on social media space is currently a serious issue. The undemanding access to the enormous amount of information being generated on these platforms has led people to post and react with toxic content that…
Inspite the emerging importance of Speech Emotion Recognition (SER), the state-of-the-art accuracy is quite low and needs improvement to make commercial applications of SER viable. A key underlying reason for the low accuracy is the…
Behavioural testing -- verifying system capabilities by validating human-designed input-output pairs -- is an alternative evaluation method of natural language processing systems proposed to address the shortcomings of the standard…
Gender-bias stereotypes have recently raised significant ethical concerns in natural language processing. However, progress in detection and evaluation of gender bias in natural language understanding through inference is limited and…
Automated bias detection in news text is heavily used to support journalistic analysis and media accountability, yet little is known about how bias detection models arrive at their decisions or why they fail. In this work, we present a…
The rise of online platforms exacerbated the spread of hate speech, demanding scalable and effective detection. However, the accuracy of hate speech detection systems heavily relies on human-labeled data, which is inherently susceptible to…
This paper investigates how hate speech varies in systematic ways according to the identities it targets. Across multiple hate speech datasets annotated for targeted identities, we find that classifiers trained on hate speech targeting…
Hate speech online remains an understudied issue for marginalized communities, particularly in the Global South, which includes developing societies with increasing internet penetration. In this paper, we aim to provide marginalized…