A Summarization System for Scientific Documents
This work addresses the need for efficient discovery and understanding of scientific literature, particularly in Computer Science, but it appears incremental as it builds on existing summarization and retrieval techniques.
The researchers tackled the problem of summarizing scientific documents by developing a system that retrieves and summarizes papers based on user queries, validated through a qualitative user study and expert evaluation.
We present a novel system providing summaries for Computer Science publications. Through a qualitative user study, we identified the most valuable scenarios for discovery, exploration and understanding of scientific documents. Based on these findings, we built a system that retrieves and summarizes scientific documents for a given information need, either in form of a free-text query or by choosing categorized values such as scientific tasks, datasets and more. Our system ingested 270,000 papers, and its summarization module aims to generate concise yet detailed summaries. We validated our approach with human experts.