On the Semantic Representation and Extraction of Complex Category Descriptors
Download as PPTX, PDF1 like856 views
The document discusses the semantic representation and extraction of natural language category descriptors (NLCDs), emphasizing the need for structured data in the era of big data. An integrated approach for NLCD representation and extraction was developed, achieving around 75% extraction accuracy. The authors highlight limitations such as the need for a formal definition of NLCDs and improvements in entity recognition and linking.
On the Semantic Representation and Extraction of Complex Category Descriptors
- 1. On the Semantic Representation and Extraction of Complex Category Descriptors André Freitas, Rafael Vieira, Edward Curry, Danilo Carvalho, João C. Pereira da Silva Insight Centre for Data Analytics NLDB 2014 Montpellier, France
- 2. Outline Motivation Extracting Natural Language Category Descriptors (NLCDs) Evaluation Summary 2
- 3. Motivation 3
- 4. Big Data Vision: More complete data-based picture of the world for systems and users. 4
- 5. “Schema” Growth & Complexity Fundamental shift in the database landscape How to build large ‘schemas’? 10s-100s attributes 1,000s-1,000,000s attributes 5
- 6. Target Motivational Scenario: Wikipedia Decentralized content generation 300,000 editors have edited Wikipedia more than 10 times > 280,000 distinct Natural Language Category Descriptors (NLCDs) 6
- 7. Natural Language Category Descriptors (NLCDs) 7
- 8. NLCDs Natural Language Category Descriptors (NLCDs) are natural language descriptors for sets Simple NLCDs: - ‘People’ - ‘Countries’ - ‘Films’ Complex NLCDs: - ‘French Senators Of The Second Empire’ - ‘United Kingdom Parliamentary Constituencies Represented By A Sitting Prime Minister’ Goal: - Parse NLCDs into an integrated structured graph 8
- 9. Assumptions N L C D NLCDs as a more syntactically tractable subset of natural language NLCDs as a low effort interface for structuring a domain of discourse IE 9
- 10. Formality vs. Usability Spectrum NLCDss NLCD graphss Information Extraction 10 NLCD graphss
- 11. Applications Database Creation Semantic Annotation Entity/Semantic Search 11
- 12. Other Examples IFRS and US GAAP - ‘Partially owned properties’ - ‘Residential portfolio segment’ - ‘Assets arising from exploration for and evaluation of mineral resources’ - ‘Key management personnel compensation’ - ‘Other long-term employee benefits’ 12
- 13. Extracting Natural Language Category Descriptors (NLCDs) 13
- 14. Natural Language Category Descriptors What is Big Data? 14
- 15. Core Features Manual analysis of 10,000 NLCDs. 15
- 17. Number of distinct POS Tag patterns 17
- 19. Focus of the Representation Taxonomic Structure Context Representation (Open Relation Extraction) - Reification-based
- 20. Examples 20
- 21. Examples 21
- 22. Examples 22
- 23. Examples 23
- 25. NLCD Extractor: POS Tagging 25
- 27. NLCD Extractor: Named Entity Recognition 27
- 28. NLCD Extractor: Core Detection 28
- 30. NLCD Extractor: Entity Linking 30 Dbpedia
- 31. NLCD Extractor: RDF Representation 31 Dbpedia
- 33. Evaluation 33
- 34. Evaluation Setup Total of 287,957 English Wikipedia categories (Open Domain scenario) Selected random sample of 2,696 categories Manual evaluation of the core extraction features - Entity segmentation - Relation identification - Unary operators - Specialization relations - Category core identification - Entity core identification - Word Sense Disambiguation (WordNet) - Entity linking (DBpedia) 34
- 35. Results Performance: - (i) graph extraction time: 9.8 ms per graph - (ii) word sense disambiguation: 121.0 ms per word - (iii) entity linking: 530.0 ms per link * i5-3317U (1.70GHz) CPU computer with 4GB RAM (4 core, 2 threads per core). 35
- 36. Summary NLCDs can provide a more tractable (from the IE perspective) natural language interface for structuring large KBs We developed an approach for the representation, extraction and integration of NLCDs - ~75% extraction accuracy Limitations: - Need for a more principled and formal definition for a NLCD - Need for a better entity recognition and linking approach Future Work: evaluation under a domain-specific scenario 36