Discourse Level
Discourse-level analysis examines how language unfolds beyond individual sentences, focusing on the structure, coherence, and pragmatic implications of extended text. Current research investigates how discourse context influences meaning, particularly in areas like large language model (LLM) comprehension, the detection of implicit information (e.g., in superlatives or narratives), and the analysis of social phenomena like dehumanization in media. This work is crucial for improving natural language processing (NLP) systems, enhancing human-computer interaction, and providing insights into social dynamics and communication breakdowns in fields like clinical linguistics.
Papers
Surprise! Uniform Information Density Isn't the Whole Story: Predicting Surprisal Contours in Long-form Discourse
Eleftheria Tsipidi, Franz Nowak, Ryan Cotterell, Ethan Wilcox, Mario Giulianelli, Alex Warstadt
Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection
Jianfei He, Lilin Wang, Jiaying Wang, Zhenyu Liu, Hongbin Na, Zimu Wang, Wei Wang, Qi Chen