Tuhin Chakrabarty

The curious case of Figurative Language

My model is sometimes more creative than I can be IRL

Despite the ubiquity of figurative language across various forms of speech and writing, the vast majority of NLP research focuses primarily on literal language. Figurative language is challenging because of its implicit nature. In this talk I will specifically focus on the following questions 1) Can Large Language Models understand/interpret them? 2) Can computers generate figurative language such as Sarcasm, Simile, Metaphor.

Tuhin is a Ph.D. student at Columbia University (based in NYC) advised by Smaranda Muresan. Tuhin’s interests are language understanding and generation especially non-literal language which requires world knowledge or commonsense reasoning

Presentation Materials

Talk Video