Recent advances in eXplainable AI (XAI) have provided new insights into ...
Without proper safeguards, large language models will readily follow
mal...
The zero-shot learning capabilities of large language models (LLMs) make...
Many NLP tasks exhibit human label variation, where different annotators...
As 3rd-person pronoun usage shifts to include novel forms, e.g., neopron...
Detecting misinformation threads is crucial to guarantee a healthy
envir...
We commonly use agreement measures to assess the utility of judgements m...
Increasingly taking place in online spaces, modern political conversatio...
Pre-trained language models (PLMs) have outperformed other NLP models on...
Fairness and environmental impact are important research directions for ...
Well-annotated data is a prerequisite for good Natural Language Processi...
The most common ways to explore latent document dimensions are topic mod...
Hate speech is a global phenomenon, but most hate speech datasets so far...
Work on hate speech has made the consideration of rude and harmful examp...
Language is constantly changing and evolving, leaving language models to...
Demographic factors (e.g., gender or age) shape our language. Previous w...
Sociodemographic factors (e.g., gender or age) shape our language. Previ...
Natural Language Processing (NLP) models risk overfitting to specific te...
The world of pronouns is changing. From a closed class of words with few...
Twitter data have become essential to Natural Language Processing (NLP) ...
How much does a CEO's personality impact the performance of their compan...
Labelled data is the foundation of most natural language processing task...
Meaning is context-dependent, but many properties of language (should) r...
Over the last several years, end-to-end neural conversational agents hav...
Many data sets in a domain (reviews, forums, news, etc.) exist in parall...
Topic models extract meaningful groups of words from documents, allowing...
Recently, Natural Language Processing (NLP) has witnessed an impressive
...
We introduce initial groundwork for estimating suicide risk and mental h...
Most state-of-the-art information extraction approaches rely on token-le...