Related papers: Semantic Gradients Interactions in SSD: A Case Stu…
Hate speech is plaguing the cyberspace along with user-generated content. This paper investigates the role of conversational context in the annotation and detection of online hate and counter speech, where context is defined as the…
Automated grading systems can efficiently score short-answer responses, yet they often fail to indicate when a grading decision is uncertain or potentially contentious. We introduce semantic entropy, a measure of variability across multiple…
Spontaneous speech emotion data usually contain perceptual grades where graders assign emotion score after listening to the speech files. Such perceptual grades introduce uncertainty in labels due to grader opinion variation. Grader…
We study Socially Unacceptable Discourse (SUD) characterization and detection in online text. We first build and present a novel corpus that contains a large variety of manually annotated texts from different online sources used so far in…
Large language models present challenges for principled uncertainty quantification, in part due to their complexity and the diversity of their outputs. Semantic dispersion, or the variance in the meaning of sampled answers, has been…
Task-specific scores are often used to optimize for and evaluate the performance of conditional text generation systems. However, such scores are non-differentiable and cannot be used in the standard supervised learning paradigm. Hence,…
Depression, a prevalent mental health disorder impacting millions globally, demands reliable assessment systems. Unlike previous studies that focus solely on either detecting depression or predicting its severity, our work identifies…
The rapid increase in hate speech on social media has exposed an unprecedented impact on society, making automated methods for detecting such content important. Unlike prior black-box models, we propose a novel transparent method for…
Sequential Social Dilemmas (SSDs) provide a key framework for studying how cooperation emerges when individual incentives conflict with collective welfare. In Multi-Agent Reinforcement Learning, these problems are often addressed by…
Gradient-based explanation methods play an important role in the field of interpreting complex deep neural networks for NLP models. However, the existing work has shown that the gradients of a model are unstable and easily manipulable,…
In recent years, monitoring hate speech and offensive language on social media platforms has become paramount due to its widespread usage among all age groups, races, and ethnicities. Consequently, there have been substantial research…
Utilizing Self-Supervised Learning (SSL) models for Speech Emotion Recognition (SER) has proven effective, yet limited research has explored cross-lingual scenarios. This study presents a comparative analysis between human performance and…
Hate speech frequently appears on social media platforms and urgently needs to be effectively controlled. Alleviating the bias caused by hate speech can help resolve various ethical issues. Although existing research has constructed several…
Amidst the rapid expansion of Machine Learning (ML) and Large Language Models (LLMs), understanding the semantics within their mechanisms is vital. Causal analyses define semantics, while gradient-based methods are essential to eXplainable…
Hate speech relies heavily on cultural influences, leading to varying individual interpretations. For that reason, we propose a Semantic Componential Analysis (SCA) framework for a cross-cultural and cross-domain analysis of hate speech…
A significant challenge in automating hate speech detection on social media is distinguishing hate speech from regular and offensive language. These identify an essential category of content that web filters seek to remove. Only automated…
Though majority vote among annotators is typically used for ground truth labels in natural language processing, annotator disagreement in tasks such as hate speech detection may reflect differences in opinion across groups, not noise. Thus,…
The evaluative character of a word is called its semantic orientation. Positive semantic orientation indicates praise (e.g., "honest", "intrepid") and negative semantic orientation indicates criticism (e.g., "disturbing", "superfluous").…
Offensive or antagonistic language targeted at individuals and social groups based on their personal characteristics (also known as cyber hate speech or cyberhate) has been frequently posted and widely circulated viathe World Wide Web. This…
Online hate speech is an important issue that breaks the cohesiveness of online social communities and even raises public safety concerns in our societies. Motivated by this rising issue, researchers have developed many traditional machine…