Skip to Main Content
Everyone (Public)

NLP/LLM Interest Group

Illuminating Literature Trends with Time-Structured Manifold Projections

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.

Speaker

Contacts

Host Organization

Admission

Free

Event Type

Lectures and Seminars

Tag

Next upcoming occurrences of this event

May 20264Monday