相关论文: Toxicity Detection Should Measure Contextual Harm,…

Digital forensic investigations increasingly rely on heterogeneous evidence such as images, scanned documents, and contextual reports. These artifacts may contain explicit or implicit expressions of harm, hate, threat, violence, or…

While automatic response generation for building chatbot systems has drawn a lot of attention recently, there is limited understanding on when we need to consider the linguistic context of an input text in the generation process. The task…

On the world wide web, toxic content detectors are a crucial line of defense against potentially hateful and offensive messages. As such, building highly effective classifiers that enable a safer internet is an important research area.…

Recent deep learning models have demonstrated strong capabilities for classifying text and non-text components in natural images. They extract a high-level feature computed globally from a whole image component (patch), where the cluttered…

Slot Filling (SF) is one of the sub-tasks of Spoken Language Understanding (SLU) which aims to extract semantic constituents from a given natural language utterance. It is formulated as a sequence labeling task. Recently, it has been shown…

The widespread dissemination of toxic content on social media poses a serious threat to both online environments and public discourse, highlighting the urgent need for detoxification methods that effectively remove toxicity while preserving…

To reduce the toxic degeneration in a pretrained Language Model (LM), previous work on Language Model detoxification has focused on reducing the toxicity of the generation itself (self-toxicity) without consideration of the context. As a…

Recent advances in natural language processing have enabled the increasing use of text data in causal inference, particularly for adjusting confounding factors in treatment effect estimation. Although high-dimensional text can encode rich…

Written language is complex. A written text can be considered an attempt to convey a meaningful message which ends up being constrained by language rules, context dependence and highly redundant in its use of resources. Despite all these…

In cognitive psychology, automatic and self-reinforcing irrational thought patterns are known as cognitive distortions. Left unchecked, patients exhibiting these types of thoughts can become stuck in negative feedback loops of unhealthy…

Hate speech detection is a crucial area of research in natural language processing, essential for ensuring online community safety. However, detecting implicit hate speech, where harmful intent is conveyed in subtle or indirect ways,…

Compromised accounts on social networks are regular user accounts that have been taken over by an entity with malicious intent. Since the adversary exploits the already established trust of a compromised account, it is crucial to detect…

This paper introduces RiskCards, a framework for structured assessment and documentation of risks associated with an application of language models. As with all language, text generated by language models can be harmful, or used to bring…

An evaluation metric is an absolute necessity for measuring the performance of any system and complexity of any data. In this paper, we have discussed how to determine the level of complexity of code-mixed social media texts that are…

LLM context is not just tokens; it is a set of commitments. Long-running conversations accumulate goals, constraints, decisions, preferences, tool results, retrieved evidence, artifacts, and safety boundaries that future responses must…

The proliferation of social media platforms has led to an increase in the spread of hate speech, particularly targeting vulnerable communities. Unfortunately, existing methods for automatically identifying and blocking toxic language rely…

This Ph.D. proposal introduces a plan to develop a computational framework to identify Self-aspects in text. The Self is a multifaceted construct and it is reflected in language. While it is described across disciplines like cognitive…

Metonymy is a figure of speech in which an entity is referred to by another related entity. The task of metonymy detection aims to distinguish metonymic tokens from literal ones. Until now, metonymy detection methods attempt to disambiguate…

The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks. To defend against such attacks, a growing body…

Measuring the performance of text recognition and text line detection engines is an important step to objectively compare systems and their configuration. There exist well-established measures for both tasks separately. However, there is no…