Extracting Summary Knowledge Graphs from Long Documents
This work addresses the challenge of summarizing long documents into structured knowledge graphs, which is incremental as it builds on existing graph learning and text summarization methods.
The paper tackles the problem of extracting compact knowledge graphs from long documents to aid in summarization and reasoning, by introducing a new text-to-graph task and developing a dataset of 200k document/graph pairs with strong baselines for evaluation.
Knowledge graphs capture entities and relations from long documents and can facilitate reasoning in many downstream applications. Extracting compact knowledge graphs containing only salient entities and relations is important but challenging for understanding and summarizing long documents. We introduce a new text-to-graph task of predicting summarized knowledge graphs from long documents. We develop a dataset of 200k document/graph pairs using automatic and human annotations. We also develop strong baselines for this task based on graph learning and text summarization, and provide quantitative and qualitative studies of their effect.