2023
EMNLP
EMNLP 2023
Anchors in Embedding Space: A Simple Concept Tracking Approach to Support Conceptual History Research
Abstract
AbstractWe introduce a simple concept tracking approach to support conceptual history research. Building on the existing practices of conceptual historians, we use dictionaries to identify “anchors”, which represent primary dimensions of meaning of a concept. Then, we create a plot showing how a key concept has evolved over time in a historical corpus in relation to these dimensions. We demonstrate the approach by plotting the change of several key concepts in the COHA corpus.
🧭
Keyword Pioneer
— concept tracking
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio