Conceptual Tool
Conceptual tools encompass a broad range of methods and models designed to represent and utilize abstract knowledge for enhanced reasoning and problem-solving. Current research focuses on developing and applying these tools across diverse fields, including AI explainability, neurorehabilitation, and qualitative analysis, often employing natural language processing (NLP) techniques and large language models (LLMs) to facilitate knowledge representation and inference. This work aims to improve the understanding and application of abstract concepts in various domains, leading to more effective and explainable AI systems, improved human-computer interaction, and more efficient knowledge transfer across disciplines.
Papers
It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance
Arjun Subramonian, Xingdi Yuan, Hal Daumé, Su Lin Blodgett
A Crosslingual Investigation of Conceptualization in 1335 Languages
Yihong Liu, Haotian Ye, Leonie Weissweiler, Philipp Wicke, Renhao Pei, Robert Zangenfeind, Hinrich Schütze