Papers by Tollef Emil JÃ, rgensen

2 papers
Cross-Lingual Sentence Compression for Length-Constrained Subtitles in Low-Resource Settings (2025.coling-main)

Copied to clipboard

Challenge: a new system for sentence compression is developed for broadcast and live media . the goal is to reduce the on-screen visual constraints of the text .
Approach: They develop a machine translation and sentence compression system that trains on openly available parallel corpora organized by compression ratios.
Outcome: The proposed system preserves high semantic meaning and metric evaluations for compressed contexts.
Enhancing Criminal Investigation Analysis with Summarization and Memory-based Retrieval-Augmented Generation: A Comprehensive Evaluation of Real Case Data (2025.coling-main)

Copied to clipboard

Challenge: KriRAG is a new architecture designed to assist criminal investigators in analyzing information and overcoming the challenge of information overload.
Approach: They propose a Retrieval-Augmented Generation architecture that structures and summarizes extensive document collections based on existing investigative queries.
Outcome: The proposed architecture is based on two homicide case files comprising approximately 3,700 documents and 13,000 pages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations