Download Now Free registration required
Using content-specific models to guide information retrieval and extraction can provide richer interfaces to endusers for both understanding the context of news events and navigating related news papers. In this paper the authors discuss a system, Brussell, that uses semantic models to organize retrieval and extraction results, generating both storylines explaining how news event situations unfold and also biographical sketches of the situation participants. They generalize these models to introduce a new category of knowledge representation, an explanatory structure, that can scale up to include information from hundreds of documents, yet still provide model-based UI support to end-users.
- Format: PDF
- Size: 714 KB