WordNet

WordNet is a lexical database for the English language.[1] It groups English words into sets of synonyms called synsets, provides short definitions and usage examples, and records a number of relations among these synonym sets or their members. WordNet can thus be seen as a combination of dictionary and thesaurus. While it is accessible to human users via a web browser,[2] its primary use is in automatic text analysis and artificial intelligence applications. The database and software tools have been released under a BSD style license and are freely available for download from the WordNet website. Both the lexicographic data (lexicographer files) and the compiler (called grind) for producing the distributed database are available.

This is an snapshot of WordNet's definition of itself.

History and team members

WordNet was created in the Cognitive Science Laboratory of Princeton University under the direction of psychology professor George Armitage Miller starting in 1985 and has been directed in recent years by Christiane Fellbaum. The project received funding from government agencies including the National Science Foundation, DARPA, the Disruptive Technology Office (formerly the Advanced Research and Development Activity), and REFLEX. George Miller and Christiane Fellbaum were awarded the 2006 Antonio Zampolli Prize for their work with WordNet.

Database contents

Example entry "Hamburger" in WordNet

As of November 2012 WordNet's latest Online-version is 3.1.[3] The database contains 155,287 words organized in 117,659 synsets for a total of 206,941 word-sense pairs; in compressed form, it is about 12 megabytes in size.[4]

WordNet includes the lexical categories nouns, verbs, adjectives and adverbs but ignores prepositions, determiners and other function words.

Words from the same lexical category that are roughly synonymous are grouped into synsets. Synsets include simplex words as well as collocations like "eat out" and "car pool." The different senses of a polysemous word form are assigned to different synsets. The meaning of a synset is further clarified with a short defining gloss and one or more usage examples. An example adjective synset is:

good, right, ripe – (most suitable or right for a particular purpose; "a good time to plant tomatoes"; "the right time to act"; "the time is ripe for great sociological changes")

All synsets are connected to other synsets by means of semantic relations. These relations, which are not all shared by all lexical categories, include:

These semantic relations hold among all members of the linked synsets. Individual synset members (words) can also be connected with lexical relations. For example, (one sense of) the noun "director" is linked to (one sense of) the verb "direct" from which it is derived via a "morphosemantic" link.

The morphology functions of the software distributed with the database try to deduce the lemma or stem form of a word from the user's input. Irregular forms are stored in a list, and looking up "ate" will return "eat," for example.

Knowledge structure

Both nouns and verbs are organized into hierarchies, defined by hypernym or IS A relationships. For instance, one sense of the word dog is found following hypernym hierarchy; the words at the same level represent synset members. Each set of synonyms has a unique index.

dog, domestic dog, Canis familiaris
    => canine, canid
       => carnivore
         => placental, placental mammal, eutherian, eutherian mammal
           => mammal
             => vertebrate, craniate
               => chordate
                 => animal, animate being, beast, brute, creature, fauna
                   => ...

At the top level, these hierarchies are organized into 25 beginner "trees" for nouns and 15 for verbs (called lexicographic files at a maintenance level). All are linked to a unique beginner synset, "entity." Noun hierarchies are far deeper than verb hierarchies

Adjectives are not organized into hierarchical trees. Instead, two "central" antonyms such as "hot" and "cold" form binary poles, while 'satellite' synonyms such as "steaming" and "chilly" connect to their respective poles via a "similarity" relations. The adjectives can be visualized in this way as "dumbbells" rather than as "trees."

Psycholinguistic aspects of WordNet

The initial goal of the WordNet project was to build a lexical database that would be consistent with theories of human semantic memory developed in the late 1960s. Psychological experiments indicated that speakers organized their knowledge of concepts in an economic, hierarchical fashion. Retrieval time required to access conceptual knowledge seemed to be directly related to the number of hierarchies the speaker needed to "traverse" to access the knowledge. Thus, speakers could more quickly verify that canaries can sing because a canary is a songbird ("sing" is a property stored on the same level as "canary"), but required slightly more time to verify that canaries can fly (where they had to access the concept "bird" on the superordinate level) and even more time to verify canaries have skin (requiring look-up across multiple levels of hyponymy, up to "animal").[5] While such experiments and the underlying theories have been subject to criticism, some of WordNet's organization is consistent with experimental evidence. For example, anomic aphasia selectively affects speakers' ability to produce words from a specific semantic category, a WordNet hierarchy. Antonymous adjectives (WordNet's central adjectives in the dumbbell structure) are found to co-occur far more frequently than chance, a fact that has been found to hold for many languages.

WordNet as a lexical ontology

WordNet is sometimes called an ontology, a persistent claim that its creators do not make. The hypernym/hyponym relationships among the noun synsets can be interpreted as specialization relations among conceptual categories. In other words, WordNet can be interpreted and used as a lexical ontology in the computer science sense. However, such an ontology should normally be corrected before being used since it contains hundreds of basic semantic inconsistencies such as (i) the existence of common specializations for exclusive categories and (ii) redundancies in the specialization hierarchy. Furthermore, transforming WordNet into a lexical ontology usable for knowledge representation should normally also involve (i) distinguishing the specialization relations into subtypeOf and instanceOf relations, and (ii) associating intuitive unique identifiers to each category. Although such corrections and transformations have been performed and documented as part of the integration of WordNet 1.7 into the cooperatively updatable knowledge base of WebKB-2,[6] most projects claiming to re-use WordNet for knowledge-based applications (typically, knowledge-oriented information retrieval) simply re-use it directly.

WordNet has also been converted to a formal specification, by means of a hybrid bottom-up top-down methodology to automatically extract association relations from WordNet, and interpret these associations in terms of a set of conceptual relations, formally defined in the DOLCE foundational ontology.[7]

In most works that claim to have integrated WordNet into ontologies, the content of WordNet has not simply been corrected when it seemed necessary; instead, WordNet has been heavily re-interpreted and updated whenever suitable. This was the case when, for example, the top-level ontology of WordNet was re-structured[8] according to the OntoClean based approach or when WordNet was used as a primary source for constructing the lower classes of the SENSUS ontology.

Limitations

WordNet does not include information about the etymology or the pronunciation of words and it contains only limited information about usage. WordNet aims to cover most of everyday English and does not include much domain-specific terminology.

WordNet is the most commonly used computational lexicon of English for word sense disambiguation (WSD), a task aimed to assigning the context-appropriate meanings (i.e. synset members) to words in a text.[9] However, it has been argued that WordNet encodes sense distinctions that are too fine-grained. This issue prevents WSD systems from achieving a level of performance comparable to that of humans, who do not always agree when confronted with the task of selecting a sense from a dictionary that matches a word in a context. The granularity issue has been tackled by proposing clustering methods that automatically group together similar senses of the same word.[10][11][12]

Licensed vs. Open WordNets

Some wordnets were subsequently created for other languages. A 2012 survey lists the wordnets and their availability.[13] In an effort to propagate the usage of WordNets, the Global WordNet community had been slowly re-licensing their WordNets to an open domain where researchers and developers can easily access and use WordNets as language resources to provide ontological and lexical knowledge in Natural Language Processing tasks.

The Open Multilingual WordNet[14] provides access to open licensed wordnets in a variety of languages, all linked to the Princeton Wordnet of English (PWN). The goal is to make it easy to use wordnets in multiple languages.

Applications

WordNet has been used for a number of different purposes in information systems, including word-sense disambiguation, information retrieval, automatic text classification, automatic text summarization, machine translation and even automatic crossword puzzle generation.

A common use of WordNet is to determine the similarity between words. Various algorithms have been proposed, and these include measuring the distance among the words and synsets in WordNet's graph structure, such as by counting the number of edges among synsets. The intuition is that the closer two words or synsets are, the closer their meaning. A number of WordNet-based word similarity algorithms are implemented in a Perl package called WordNet::Similarity,[15] and in a Python package called NLTK. Other more sophisticated WordNet-based similarity techniques include ADW,[16] whose implementation is available in Java. WordNet can also be used to inter-link other vocabularies.[17]

Interfaces

Princeton maintains a list of related projects[18] that includes links to some of the widely used application programming interfaces available for accessing WordNet using various programming languages and environments.

Related projects and extensions

WordNet is connected to several databases of the Semantic Web. WordNet is also commonly re-used via mappings between the WordNet synsets and the categories from ontologies. Most often, only the top-level categories of WordNet are mapped.

Global WordNet Association

The Global WordNet Association (GWA)[19] is a public and non-commercial organization that provides a platform for discussing, sharing and connecting wordnets for all languages in the world. The GWA also promotes the standardization of wordnets across different languages to ensure its uniformity in enumerating the different synsets in human languages. The GWA keeps a list of wordnets developed around the world.[20]

Other languages

Linked data

Related projects

Distributions

WordNet Database is distributed as a dictionary package (usually a single file) for the following software:

See also

References

  1. G. A. Miller, R. Beckwith, C. D. Fellbaum, D. Gross, K. Miller. 1990. WordNet: An online lexical database. Int. J. Lexicograph. 3, 4, pp. 235–244.
  2. "WordNet Search - 3.1".
  3. "Current WordNet version". Wordnet.princeton.edu. 2012-11-09. Retrieved 2014-03-11.
  4. "WordNet Statistics". Wordnet.princeton.edu. Retrieved 2014-03-11.
  5. Collins A., Quillian M. R. 1972. Experiments on Semantic Memory and Language Comprehension. In Cognition in Learning and Memory. Wiley, New York.
  6. http://www.phmartin.info. "Integration of WordNet 1.7 in WebKB-2". Webkb.org. Retrieved 2014-03-11.
  7. Gangemi, A.; Navigli, R.; Velardi, P. (2003). The OntoWordNet Project: Extension and Axiomatization of Conceptual Relations in WordNet (PDF). Proc. of International Conference on Ontologies, Databases and Applications of SEmantics (ODBASE 2003) (Catania, Sicily (Italy)). pp. 820–838.
  8. Oltramari, A.; Gangemi, A.; Guarino, N.; Masolo, C. (2002). Restructuring WordNet's Top-Level: The OntoClean approach. OntoLex'2 Workshop, Ontologies and Lexical Knowledge Bases (LREC 2002). Las Palmas, Spain. pp. 17–26. CiteSeerX: 10.1.1.19.6574.
  9. R. Navigli. Word Sense Disambiguation: A Survey, ACM Computing Surveys, 41(2), 2009, pp. 1–69
  10. E. Agirre, O. Lopez. 2003. Clustering WordNet Word Senses. In Proc. of the Conference on Recent Advances on Natural Language (RANLP’03), Borovetz, Bulgaria, pp. 121–130.
  11. R. Navigli. Meaningful Clustering of Senses Helps Boost Word Sense Disambiguation Performance, In Proc. of the 44th Annual Meeting of the Association for Computational Linguistics joint with the 21st International Conference on Computational Linguistics (COLING-ACL 2006), Sydney, Australia, July 17-21st, 2006, pp. 105–112.
  12. R. Snow, S. Prakash, D. Jurafsky, A. Y. Ng. 2007. Learning to Merge Word Senses, In Proc. of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), Prague, Czech Republic, pp. 1005–1014.
  13. Francis Bond and Kyonghee Paik 2012a. A survey of wordnets and their licenses. In Proceedings of the 6th Global WordNet Conference (GWC 2012). Matsue. 64–71
  14. http://compling.hss.ntu.edu.sg/omw/
  15. "Ted Pedersen - WordNet::Similarity". D.umn.edu. 2008-06-16. Retrieved 2014-03-11.
  16. M. T. Pilehvar, D. Jurgens and R. Navigli. Align, Disambiguate and Walk: A Unified Approach for Measuring Semantic Similarity.. Proc. of the 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013), Sofia, Bulgaria, August 4–9, 2013, pp. 1341-1351.
  17. Ballatore A, et al. (2014). "Linking geographic vocabularies through WordNet". Annals of GIS 20 (2).
  18. "Related projects - WordNet - Related projects". Wordnet.princeton.edu. 2014-01-06. Retrieved 2014-03-11.
  19. The Global WordNet Association (2010-02-04). "globalwordnet.org". globalwordnet.org. Retrieved 2014-03-11.
  20. "Wordnets in the World". Archived from the original on 2011-10-21.
  21. Chinese Wordnet (中文詞彙網路) official page at National Taiwan University
  22. S. Benoît, F. Darja. 2008. Building a free French wordnet from multilingual resources. In Proc. of Ontolex 2008, Marrakech, Maroc.
  23. C. Mouton, G. de Chalendar. 2010.JAWS : Just Another WordNet Subset. In Proc. of TALN 2010.
  24. Pushpak Bhattacharyya, IndoWordNet, Lexical Resources Engineering Conference 2010 (LREC 2010), Malta, May, 2010.
  25. E. Pianta, L. Bentivogli, C. Girardi. 2002. MultiWordNet: Developing an aligned multilingual database. In Proc. of the 1st International Conference on Global WordNet, Mysore, India, pp. 21–25.
  26. P. Vossen, Ed. 1998. EuroWordNet: A Multilingual Database with Lexical Semantic Networks. Kluwer, Dordrecht, The Netherlands.
  27. "The Global WordNet Association". Globalwordnet.org. 2010-02-04. Retrieved 2014-01-05.
  28. D. Tufis, D. Cristea, S. Stamou. 2004. Balkanet: Aims, methods, results and perspectives. A general overview. Romanian J. Sci. Tech. Inform. (Special Issue on Balkanet), 7(1-2), pp. 9–43.
  29. "UWN: Towards a Universal Multilingual Wordnet - D5: Databases and Information Systems (Max-Planck-Institut für Informatik)". Mpi-inf.mpg.de. 2011-08-14. Retrieved 2014-01-05.
  30. "Русский WordNet". Pgups.ru. Retrieved 2014-01-05.
  31. "RussNet: Главная страница". Project.phil.spbu.ru. Retrieved 2014-03-11.
  32. "FinnWordNet – The Finnish WordNet - Department of General Linguistics". Ling.helsinki.fi. Retrieved 2014-01-05.
  33. "GermaNet". Sfs.uni-tuebingen.de. Retrieved 2014-03-11.
  34. "arademaker/openWordnet-PT ¡ GitHub". Github.com. Retrieved 2014-01-05.
  35. http://plwordnet.pwr.wroc.pl/wordnet/ official webpage
  36. http://www.ltc.amu.edu.pl/polnet/ official webpage
  37. "BulNet". dcl.bas.bg. Retrieved 2015-05-07.
  38. R. Navigli, S. P. Ponzetto. BabelNet: Building a Very Large Multilingual Semantic Network. Proc. of the 48th Annual Meeting of the Association for Computational Linguistics (ACL 2010), Uppsala, Sweden, July 11–16, 2010, pp. 216–225.
  39. A. Pease, I. Niles, J. Li. 2002. The suggested upper merged ontology: A large ontology for the Semantic Web and its applications. In Proc. of the AAAI-2002 Workshop on Ontologies and the Semantic Web, Edmonton, Canada.
  40. S. Reed and D. Lenat. 2002. Mapping Ontologies into Cyc. In Proc. of AAAI 2002 Conference Workshop on Ontologies For The Semantic Web, Edmonton, Canada, 2002
  41. Masolo, C., Borgo, S., Gangemi, A., Guarino, N., Oltramari, A., Schneider, L.S. 2002. WonderWeb Deliverable D17. The WonderWeb Library of Foundational Ontologies and the DOLCE ontology. Report (ver. 2.0, 15-08-2002)
  42. Gangemi, A., Guarino, N., Masolo, C., Oltramari, A. 2003 Sweetening WordNet with DOLCE. In AI Magazine 24(3): Fall 2003, pp. 13–24
  43. C. Bizer, J. Lehmann, G. Kobilarov, S. Auer, C. Becker, R. Cyganiak, S. Hellmann, DBpedia – A crystallization point for the Web of Data. Web Semantics, 7(3), 2009, pp. 154–165
  44. S. M. Harabagiu, G. A. Miller, D. I. Moldovan. 1999. WordNet 2 – A Morphologically and Semantically Enhanced Resource. In Proc. of the ACL SIGLEX Workshop: Standardizing Lexical Resources, pp. 1–8.
  45. J. Deng, W. Dong, R. Socher, L. Li, K. Li, L. Fei-Fei. ImageNet: A Large-Scale Hierarchical Image Database. In Proc. of 2009 IEEE Conference on Computer Vision and Pattern Recognition
  46. M. Poprat, E. Beisswanger, U. Hahn. 2008. Building a BIOWORDNET by Using WORDNET’s Data Formats and WORDNET’s Software Infrastructure – A Failure Story. In Proc. of the Software Engineering, Testing, and Quality Assurance for Natural Language Processing Workshop, pp. 31–39.
  47. S. Ponzetto, R. Navigli. Large-Scale Taxonomy Mapping for Restructuring and Integrating Wikipedia, In Proc. of the 21st International Joint Conference on Artificial Intelligence (IJCAI 2009), Pasadena, California, July 14-17th, 2009, pp. 2083–2088.
  48. S. P. Ponzetto, R. Navigli. Knowledge-rich Word Sense Disambiguation rivaling supervised systems. In Proc. of the 48th Annual Meeting of the Association for Computational Linguistics (ACL), 2010, pp. 1522–1531.
  49. S. Baccianella, A. Esuli and F. Sebastiani. SentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining. In Proceedings of the 7th Conference on Language Resources and Evaluation (LREC'10), Valletta, MT, 2010, pp. 2200–2204.
  50. Piek Vossen, Claudia Soria, Monica Monachini: Wordnet-LMF: a standard representation for multilingual wordnets, in LMF Lexical Markup Framework, edited by Gil Francopoulo ISTE / Wiley 2013 (ISBN 978-1-84821-430-9)
  51. "Babylon WordNet". Babylon.com. Retrieved 2014-03-11.
  52. "GoldenDict - Browse /dictionaries at Sourceforge.net". Sourceforge.net. 2010-12-01. Retrieved 2014-01-05.
  53. "Lingoes WordNet". Lingoes.net. 2007-11-16. Retrieved 2014-03-11.

External links

This article is issued from Wikipedia - version of the Thursday, April 28, 2016. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.