5
Entityclassifier.eu: Real-time Classification of Entities in Text with Wikipedia Milan Dojchinovski 1,2 , Tomáš Kliegr 2 1 Faculty of Information Technology Czech Technical University in Prague 2 Faculty of Informatics and Statistics University of Economics, Prague European Conference on Machine Learning and Principles and Practice of Knowledge Discovery Discovery in Databases (ECMLPKDD 2013) September 23-27, 2013, Prague, CZ Milan Dojchinovski [email protected] - @m1ci - http://dojchinovski.mk Except where otherwise noted, the content of this presentation is licensed under Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported Czech Technical University in Prague University of Economics Prague

Entityclassifier. eu: Real-Time Classification of Entities in Text with Wikipedia

Embed Size (px)

DESCRIPTION

Targeted Hypernym Discovery (THD) performs unsupervised classification of entities appearing in text. A hypernym mined from the free-text of the Wikipedia article describing the entity is used as a class. The type as well as the entity are cross-linked with their representation in DBpedia, and enriched with additional types from DBpedia and YAGO knowledge bases providing a semantic web interoperability. The system, available as a web application and web service at entityclassifier.eu, currently supports English, German and Dutch.

Citation preview

Page 1: Entityclassifier. eu: Real-Time Classification of Entities in Text with Wikipedia

Entityclassifier.eu: Real-time Classification of Entities in Text with Wikipedia

Milan Dojchinovski1,2, Tomáš Kliegr2

1 Faculty of Information TechnologyCzech Technical University in Prague

2Faculty of Informatics and StatisticsUniversity of Economics, Prague

European Conference on Machine Learning and Principles and Practice of Knowledge Discovery Discovery in Databases (ECMLPKDD 2013)

September 23-27, 2013, Prague, CZ

Milan [email protected] - @m1ci - http://dojchinovski.mk

Except where otherwise noted, the content of this presentation is licensed underCreative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported

Czech Technical University in Prague

University of Economics Prague

Page 2: Entityclassifier. eu: Real-Time Classification of Entities in Text with Wikipedia

What is Entityclassifier.eu?

‣ Fully-automated Named Entity Recognition (NER) system- entity spotting - rule based lexico-syntactic patterns- entity disambiguation - unique identification with Wikipedia/DBpedia URIs- entity classification - using types from the DBpedia Ontology- entity linking - entities linked with concepts from DBpedia and YAGO

2Entityclassifier.eu: Real-time Classification of Entities in Text with Wikipedia - @m1ci - http://dojchinovski.mk

Page 3: Entityclassifier. eu: Real-Time Classification of Entities in Text with Wikipedia

Advantages of using Entityclassifier.eu

‣ Real-time mining- previously unknown entities can be disambiguated and classified in real-time‣ Right type granularity- most frequent type, as selected by the Wikipedia editors, extracted from free text

‣ Multilinguality- can process English, German and Dutch texts

3Entityclassifier.eu: Real-time Classification of Entities in Text with Wikipedia - @m1ci - http://dojchinovski.mk

Page 4: Entityclassifier. eu: Real-Time Classification of Entities in Text with Wikipedia

Availability

‣ Web application - http://entityclassfier.eu‣ REST API- API documentation http://entityclassifier.eu/thd/docs/

4Entityclassifier.eu: Real-time Classification of Entities in Text with Wikipedia - @m1ci - http://dojchinovski.mk

Live demo!http://entityclassifier.eu

Page 5: Entityclassifier. eu: Real-Time Classification of Entities in Text with Wikipedia

Feedback

5

Thank you!Questions, comments, ideas?

Milan Dojchinovski @[email protected] http://dojchinovski.mk

Except where otherwise noted, the content of this presentation is licensed underCreative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported