In the context of terrorism, reports and articles often contain extensive, unstructured text that is challenging to analyze and cross-reference in an automated manner. For instance, articles about a single terror incident might arrive at different times throughout the day, each with varying details. These reports typically include crucial entities such as persons, objects, locations, and events.
- Extract entities from these reports and represent them in a structured knowledge graph.
- Develop a chatbot capable of answering questions based on the generated knowledge graph.
First, we perform coreference resolution to clarify contexts and references within the articles. Then, our advanced Large Language Model (LLM) extracts specific entities and their relationships (entity/ relationship disambiguation), integrating them into a comprehensive knowledge graph. Articles are intelligently chunked, with entities linked to their respective extracts for precise, context-aware tracking.
For retrieval, we deploy a Multi-agent LLM system designed to excel in the high-stakes environment of terror event reporting. This system resolves complex relationships, identifies key entities, generates detailed follow-up questions, retrieves pertinent extracts, and provides concise summaries. Additionally, it features a decisor agent to make informed, real-time decisions based on the aggregated data.
Our solution transforms the overwhelming influx of terror-related articles into clear, actionable intelligence, empowering security professionals and decision-makers to respond swiftly and effectively. Stay informed, stay prepared, and make critical decisions with confidence.
construct_kgraph.ipynb Documents how to constructing the knowledge Graph
retrival.ipynb Documents how to query the Knowledge Graph
