is a web application for search and analysis over multiple sources of international and business news such as International Herald Tribune, BBC, NY Times, etc. It provides various search paradigms on top of a semantic database.
allows you to:
- Find all available documents about an event, person, organization, etc.
- Define search by keywords, entity names, conceptual relations.
- Explore links between entities occurring together in a text.
- Analyze emerging trends about entities of interest over a period of time.
In its essence, performs three basic types of search – keyword (full-text search over the texts), conceptual (pattern search over the graph of the knowledge base), and combined.
Depending on the problem you want to solve, there are multiple Search Paradigms available.
- Keyword: allows you to combine words and phrases using Logical (Boolean) Operators (such as AND, OR, and "") to limit, widen, or define your search.
- Structure: can be used for two kinds of search tasks:
- To look for entities through their names, part of their names, or entity type (Entity look-up).
- To create patterns by choosing entity types, names, and relations between them. If you want to make your search even more specific, you can use additional entity characteristics.
- Patterns: can be used for modeling frequently executed structured queries (Predefined patterns for searching entities).
- Ontology: can be used for exploration of the PROTON Ontology classes of entities and their properties.
- Facets: can be used for finding entities that co-occur with other entities and terms in the same context. In other words, it helps you find unknown entities by defining the environment in which they appear (relations with other entities, dates, or terms).
- Timelines: can be used for analyzing how entity popularity changes through time in a given set of documents; trends of entity popularity.
is based on KIM - Knowledge and Information Management, a platform for automatic semantic annotation, indexing, and retrieval of unstructured and semi-structured content.
|As the documents in the document repository may differ from the time this guide was created, the given examples may not work exactly as provided.|