Entity identification and extraction
Upcoming SlideShare
Loading in...5
×
 

Entity identification and extraction

on

  • 756 views

Research project

Research project

Statistics

Views

Total Views
756
Views on SlideShare
575
Embed Views
181

Actions

Likes
0
Downloads
13
Comments
0

1 Embed 181

http://wiki.knoesis.org 181

Accessibility

Upload Details

Uploaded via as Microsoft PowerPoint

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

Entity identification and extraction Entity identification and extraction Presentation Transcript

  • ENTITYIDENTIFICATION AND CLASSIFICATION
  • MOTIVATION :
  • Automated Entity Identification and ExtractionOBJECTIVE : Entities
  • PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> PREFIX owl: <http://www.w3.org/2002/07/owl#> SELECT ?class WHERE { ?class rdfs:subClassOf owl:Thing . ?person rdf:type ?class . ?person <http://www.w3.org/2000/01/rdf-schema#label> "Anna"@en. }APPROACH : http://dbpedia.org/ontology/Stadium http://dbpedia.org/ontology/Bacteria http://dbpedia.org/ontology/Company http://dbpedia.org/ontology/GridironFootballPlayer http://dbpedia.org/ontology/Animal http://dbpedia.org/ontology/PersonFunction http://dbpedia.org/ontology/Athlete http://dbpedia.org/ontology/School http://dbpedia.org/ontology/Governor http://dbpedia.org/ontology/Monarch http://dbpedia.org/ontology/Software http://dbpedia.org/ontology/ComicsCreator
  • APPROACH : <dbpedia>http://dbpedia.org/resource/India</dbpedia> <ciaFactbook>http://www4.wiwiss.fu- berlin.de/factbook/resource/India</ciaFactbook> <freebase>http://rdf.freebase.com/ns/guid.9202a8c04000641f8000000000 01de20</freebase> <umbel>http://umbel.org/umbel/ne/wikipedia/India</umbel> <opencyc>http://sw.opencyc.org/concept/Mx4rvVj7XJwpEbGdrcN5Y29ycA </opencyc> <yago>http://mpii.de/yago/resource/India</yago>
  • MAJOR STEPS :
  • DBPedia Query:ARCHITECTURE : Pre- Parsing processing NOUN DB TWEETS PHRASES Frequency DBPedia Endpoint CANDIDATE SET
  • Alchemy API : Pre-ARCHITECTURE : Query processing ALCHEMY API DB TWEETS type relevance name count CANDIDATE XML SET PARSER
  • RESULT ANALYSIS : PROBLEMS
  • India Corruption Royal WeddingRESULT ANALYSIS :
  • RESULT ANALYSIS : PROBLEMS
  • DBPEDIARESULT ANALYSIS : “Anna Hazare” “Anna”
  • RESULT ANALYSIS : ALCHEMY API
  • RESULT ANALYSIS : ALCHEMY API
  • RESULT ANALYSIS :
  • ALCHEMY API PROBLEMS:RESULT ANALYSIS :
  • ALCHEMY API PROBLEMS:RESULT ANALYSIS :
  • ALCHEMY API PROBLEMS:RESULT ANALYSIS :
  • ALCHEMY API PROBLEMS:RESULT ANALYSIS :
  • NOUN-PHRASES:DBPEDIA RESULTS:
  • ALCHEMY API RESULT:
  • WIKIPEDIA-BASED:
  • WIKIPEDIA-BASED:
  • String Similarity Measures:
  • String Similarity Measures:
  • STRING SIMILARITY:
  • RESULTS:Sorted list Final list ofof entities entities obtained
  • For the list of Noun-Phrases as the candidate set:EVALUATION:
  • For the DBPedia-obtained candidate set:EVALUATION:
  • For the Alchemy-API obtained candidate set:EVALUATION:
  • WHAT ELSE :
  • WHAT MORE TO DO : Relation between Entities
  • LIMITATIONS :