NLP/LLM Interest Group
Illuminating Literature Trends with Time-Structured Manifold Projections
Join our mailing list to receive Zoom Passcode: https://mailman.yale.edu/mailman/listinfo/nlp-llm-ig
Abstract: With a million scientific papers yearly, methods for organizing and exploring research are more important than ever. Though semantic embeddings combined with manifold learning algorithms like t-SNE or UMAP produce useful maps, these ignore publication date, which is crucial for understanding research progression. As a remedy, we develop a time-aware dimension reduction algorithm that groups similar papers while directly encoding date using radius in polar plots, revealing trends that would not be visible with standard t-SNE- or UMAP-based maps.
Related Media
Speaker
Contacts
Host Organization
Admission
Free
Event Type
Lectures and Seminars