ECO: A Framework for Entity Co-Occurrence Exploration with Faceted Navigation
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Even as highly structured databases and semantic knowledge bases become more prevalent, a substantial amount of human knowledge is reported as written prose. Typical textual reports, such as news articles, contain information about entities (people, organizations, and locations) and their relationships. Automatically extracting such relationships from large text corpora is a key component of corporate and government knowledge bases. The primary goal of the ECO project is to develop a scalable framework for extracting and presenting these relationships for exploration using an easily navigable faceted user interface. ECO uses entity co-occurrence relationships to identify related entities. The system aggregates and indexes information on each entity pair, allowing the user to rapidly discover and mine relational information.
- Research Organization:
- Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- W-7405-ENG-48
- OSTI ID:
- 1119939
- Report Number(s):
- LLNL-TR--450951
- Country of Publication:
- United States
- Language:
- English
Similar Records
ERMES - An entity-relationship modeling expert system
Survey of Current State of the Art Entity-Relation Extraction Tools
Automatic Labeling for Entity Extraction in Cyber Security
Journal Article
·
Mon Dec 31 23:00:00 EST 1990
· Automatic Control, Theory and Applications; (Canada)
·
OSTI ID:5515987
Survey of Current State of the Art Entity-Relation Extraction Tools
Technical Report
·
Fri May 01 00:00:00 EDT 2020
·
OSTI ID:1630263
Automatic Labeling for Entity Extraction in Cyber Security
Conference
·
Tue Dec 31 23:00:00 EST 2013
·
OSTI ID:1143555