2005 JRC Workshop Smrz

83 %
17 %
Information about 2005 JRC Workshop Smrz
Education

Published on March 6, 2008

Author: Roxie

Source: authorstream.com

Parallel Corpora for Multilingual Ontology Learning:  Parallel Corpora for Multilingual Ontology Learning Pavel Smrz Brno University of Technology Czech Republic Motivation:  Motivation Ontologies (in computer science) are formal and machine readable representations of concepts and relations among them Ontologies can be used for efficient semantic querying, relevance measurement, sharing knowledge representation and many other purposes Ontologies also play the major role in the Semantic Web vision (data on the web understandable by machines – Berners-Lee, OWL - Ontology Web Language) Slide3:  (subclass Weapon Device) (documentation Weapon "The &%Class of &%Devices that are designed primarily to damage or destroy &%Humans/&%Animals, &%StationaryArtifacts or the places inhabited by &%Humans/&%Animals.") (=> (instance ?WEAPON Weapon) (capability Damaging instrument ?WEAPON)) (=> (instance ?WEAPON Weapon) (hasPurpose ?WEAPON (exists (?DEST ?PATIENT) (and (instance ?DEST Damaging) (patient ?DEST ?PATIENT) (or (instance ?PATIENT StationaryArtifact) (instance ?PATIENT Animal) (exists (?ANIMAL) (and (instance ?ANIMAL Animal) (inhabits ?ANIMAL ?PATIENT)))))))) Motivation:  Motivation Three levels of generality of ontologies: foundational (top, upper) ontology core ontology specific domain ontology Domain ontologies provide common understanding of particular application domains Creating ontologies is extremely demanding, labor-intensive and time-consuming task Automatic acquisition (learning) of ontologies (semantic relations) from text Motivation:  Motivation Pattern-based extraction of semantic relations (M. A. Hearst, 1992) Methods for hyponymy (is-a) later adopted for other kinds of relations Token co-occurrence techniques to gather sets of concepts belonging to the same class Various combinations and modifications (D. Lin, A. Kilgarriff – WordSketches) The same methods applied for subjective language identification and opinion mining OLE – Ontology Learning Platform:  OLE – Ontology Learning Platform Based on the pattern-extraction technique Used for ontology extraction from biomedical texts Explicit representation of uncertainty - BayesOWL OLE – Ontology Learning Platform:  OLE – Ontology Learning Platform OLITE processes plain text and creates the miniontologies from the extracted data PALEA is responsible for learning of new semantic patterns OLEMAN merges the miniontologies resulting from the OLITE module and updates the base domain ontology NP1 [“,”] “such as” NPList2 NP1 (“and”|“or”) “other” NP2 The ontology of HATs:  The ontology of HATs The ontology of HATs:  The ontology of HATs Extracted Relations:  Extracted Relations Multilingual Pattern Learning:  Multilingual Pattern Learning Extraction patterns usually defined manually The task must be repeated for each new language in a multilingual environment. Parallel corpora for pattern acquisition: Patterns defined for one language (English) Semantically related expressions extracted from the given part of the corpus Translation equivalents in all other languages Patterns for the respective languages automatically derived from the corpus data Subjectivity Clue Extraction:  Subjectivity Clue Extraction CLUMSY - clue mining system for subjective language Subjectivity clues and opinion extraction patterns defined for English Data from parallel English-Czech corpus used for automatic acquisition of Czech patterns Integrated in a prototype of EPOS – a new multilingual opinion mining system EPOS – Electronic Poll System:  EPOS – Electronic Poll System Future Directions:  Future Directions Automatically extracted domain ontologies for PortaGe – e-learning portal generator Opinionated parallel texts for the development of EPOS Ontology learning from Acquis Communautaire parallel corpus – automatic acquisition of legal ontologies?

Add a comment

Related presentations

Related pages

Proper Noun Recognition and Classification Using Weighted ...

A. Kilgarriff, P. Rychly, P. Smrz, and D. Tugwell. The sketch engine. ... In Proceedings of FSMNLP 05, 2005 ... The workshop was held in Ispra ...
Read more

JRC Enlargement Action - www.research.ro

JRC ENLARGEMENT ACTION 2005 Job ... 00 94.00 42.00 69.00 24.00 Enlargement and Integration Action 2005 Experts trained in JRC workshop by gropu of ...
Read more

A Survey of Arabic Named Entity Recognition and ...

ACE 2005 corpus: This includes BN, NW, ... developed by Smrz ... In Proceedings of Workshop on Natural Language-Independent Engineering, ...
Read more

looking forward to start - Deutsch-Übersetzung – Linguee ...

On the second and third days of the workshop the participants then ... Mit April 2005 wurde ... Nebel and Matej Smrz as our riders and the ...
Read more

Syntagmatic Relations in Corpus and Learner Lexicography ...

Towards a lexico-grammar (1) Pattern (Hunston, Francis 1999), construction (Atkins, Rundell 2008), collocation (Barch 2004, Siepmann 2005) Pattern ‒ all ...
Read more

Exploiting the leipzig corpora collection | Erla ...

Exploiting the leipzig corpora collection. ... Pavel Rychly, Pavel Smrz, and David ... In Proceedings of LREC-06 workshop on Quality assurance and quality ...
Read more

Publications of NLP Centre

Publications of NLP Centre. 2016. APRESJAN, Valentina, Vít BAISA, Olga BUIVOLOVA a Olga KULTEPINA. RuSkELL: Online Language Learning Tool for Russian ...
Read more

C.: Exploiting the leipzig corpora collection (PDF ...

Official Full-Text Publication: C.: Exploiting the leipzig corpora collection on ResearchGate, the professional network for scientists.
Read more