OpenAI has released the Chat Generative Pre-trained Transformer (ChatGPT) and
revolutionized the approach in artificial intelligence to human-model interaction. The first …

Language models demonstrate both quantitative improvement and new qualitative
capabilities with increasing scale. Despite their potentially transformative impact, these new …

Contextual word representations, typically trained on unstructured, unlabeled text, do not
contain any explicit grounding to real world entities and are often unable to remember facts …

Abstract Word Sense Disambiguation (WSD) aims at making explicit the semantics of a word
in context by identifying the most suitable meaning from a predefined sense inventory …

Inductive transfer learning has greatly impacted computer vision, but existing approaches in
NLP still require task-specific modifications and training from scratch. We propose Universal …

Computational linguistics has enabled the introduction of objective tools that measure some
of the symptoms of schizophrenia, including the coherence of speech associated with formal …

Transformer architectures show significant promise for natural language processing. Given
that a single pretrained model can be fine-tuned to perform well on many different tasks …

Word Sense Disambiguation (WSD) aims to find the exact sense of an ambiguous word in a
particular context. Traditional supervised methods rarely take into consideration the lexical …

Semantic processing is a fundamental research domain in computational linguistics. In the
era of powerful pre-trained language models and large language models, the advancement …

Over the past years, distributed semantic representations have proved to be effective and
flexible keepers of prior knowledge to be integrated into downstream applications. This …