Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia
-
Upload
milan-dojchinovski -
Category
Technology
-
view
417 -
download
3
description
Transcript of Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia
![Page 1: Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia](https://reader035.fdocuments.us/reader035/viewer/2022073116/554975b5b4c905d8558b5835/html5/thumbnails/1.jpg)
Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia
Milan Dojchinovski1, Tomas Kliegr2
1 Faculty of Information TechnologyCzech Technical University in Prague
2Faculty of Informatics and StatisticsUniversity of Economics, Prague
The 7th Workshop on Intelligent and Knowledge Oriented Technologies (WIKT 2012)November 22-23, 2012, Smolenice, SK
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: Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia](https://reader035.fdocuments.us/reader035/viewer/2022073116/554975b5b4c905d8558b5835/html5/thumbnails/2.jpg)
Overview
‣ Introduction
‣ Entity Recognition, Classification and Publication
‣ Experiments
‣ Conclusion and Future Work
Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia - @m1ci - http://dojchinovski.mk 2
![Page 3: Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia](https://reader035.fdocuments.us/reader035/viewer/2022073116/554975b5b4c905d8558b5835/html5/thumbnails/3.jpg)
Introduction
‣ Unsupervised and fully-automated:- entity recognition - rule based lexico-syntactic patterns- entity classification by extraction of hypernyms - targeted hypernym extraction- entity linking to DBpedia concepts
‣ Publication as Linked Data- results in NLP Interchange Format (NIF)
3Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia - @m1ci - http://dojchinovski.mk
![Page 4: Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia](https://reader035.fdocuments.us/reader035/viewer/2022073116/554975b5b4c905d8558b5835/html5/thumbnails/4.jpg)
Overview
‣ Introduction
‣ Entity Recognition, Classification and Publication
‣ Experiments
‣ Conclusion and Future Work
Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia - @m1ci - http://dojchinovski.mk 4
![Page 5: Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia](https://reader035.fdocuments.us/reader035/viewer/2022073116/554975b5b4c905d8558b5835/html5/thumbnails/5.jpg)
Tool Architecture
5
‣ Available as Web 2.0 application at: http://ner.vse.cz/thd‣ Web API available at: http://ner.vse.cz/thd/docs
Fig 1. Architecture overview
Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia - @m1ci - http://dojchinovski.mk
![Page 6: Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia](https://reader035.fdocuments.us/reader035/viewer/2022073116/554975b5b4c905d8558b5835/html5/thumbnails/6.jpg)
Entity Recognition and Classification
6
‣ Entity Recognition- 2 JAPE grammars: 1) NNP+ 2) JJ* NN+- input: free text- output: Named (e.g., “Diego Maradona”) or Common Entities (e.g., “hockey player”)
‣ Entity Classification- supported by the Targeted Hypernym Discovery algorithm- lexico-syntactic patterns, e.g. “_x_ is a _y_ “
Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia - @m1ci - http://dojchinovski.mk
![Page 7: Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia](https://reader035.fdocuments.us/reader035/viewer/2022073116/554975b5b4c905d8558b5835/html5/thumbnails/7.jpg)
Entity Linking and Publication
7
‣ Entity Linking- linking with concepts from DBpedia- used Wikipedia Search API- mapping Wikipedia article URL to its DBpedia representation
‣ Publication in NIF- NLP Interchange Format (RDF-based representation)- each processed document (context) has unique identifier- each entity and hypernym as offset-based string
Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia - @m1ci - http://dojchinovski.mk
![Page 8: Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia](https://reader035.fdocuments.us/reader035/viewer/2022073116/554975b5b4c905d8558b5835/html5/thumbnails/8.jpg)
Overview
‣ Introduction
‣ Entity Recognition, Classification and Publication
‣ Experiments
‣ Conclusion and Future Work
Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia - @m1ci - http://dojchinovski.mk 8
![Page 9: Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia](https://reader035.fdocuments.us/reader035/viewer/2022073116/554975b5b4c905d8558b5835/html5/thumbnails/9.jpg)
Experiments
9
‣ Question addressed- How well our tool recognizes, classifies and links Named and Common Entities?
‣ Experiment setup- manually created dataset, “Czech Traveler Dataset”- 101 Named Entities, 85 Common Entities- comparison with 3 other systems: DBpedia Spotlight, Open Calais, Alchemy API
‣ Results- Named Entities,
• f-score: recognition 0.66, classification 0.66, linking 0.58
- Common Entities
• f-score: recognition 0.60, classification 0.51, linking 0.61
- better results in all tasks
• overtaken only by DBpedia Spotlight - linking of common entities with f-score 0.69
Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia - @m1ci - http://dojchinovski.mk
![Page 10: Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia](https://reader035.fdocuments.us/reader035/viewer/2022073116/554975b5b4c905d8558b5835/html5/thumbnails/10.jpg)
Overview
‣ Introduction
‣ Entity Recognition, Classification and Publication
‣ Experiments
‣ Conclusion and Future Work
Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia - @m1ci - http://dojchinovski.mk 10
![Page 11: Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia](https://reader035.fdocuments.us/reader035/viewer/2022073116/554975b5b4c905d8558b5835/html5/thumbnails/11.jpg)
Conclusion and Future Work
11
‣ Tool for Entity Recognition, Classification and Publication
‣ Future directions- multilingual support - Dutch, German and Czech language- grammar improvements- evaluation on a standard benchmark
Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia - @m1ci - http://dojchinovski.mk
![Page 12: Recognizing, Classifying and Linking Entities with Wikipedia and DBpedia](https://reader035.fdocuments.us/reader035/viewer/2022073116/554975b5b4c905d8558b5835/html5/thumbnails/12.jpg)
Feedback
12
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
demo at: http://ner.vse.cz/thd