Terminology extraction

Terminology extraction, term extraction, or glossary extraction, is a subtask of information extraction. The goal of terminology extraction is to automatically extract relevant terms from a given corpus.

In the semantic web era, a growing number of communities and networked enterprises started to access and interoperate through the internet. Modeling these communities and their information needs is important for several web applications, like topic-driven web crawlers, [Menczer F., Pant G. and Srinivasan P. : Topic-Driven Crawlers: machine learning issues [http://citeseer.ist.psu.edu/menczer02topicdriven.html] ] web services, [Fan J. and Kambhampati S. : A Snapshot of Public Web Services, in ACM SIGMOD Record archive Volume 34 , Issue 1 (March 2005). [http://portal.acm.org/citation.cfm?id=1058150.1058156] ] recommender systems, [Yan Zheng Wei, Luc Moreau, Nicholas R. Jennings: A market-based approach to recommender systems, in ACM Transactions on Information Systems (TOIS), Volume 23 Issue 3, July 2005 [http://portal.acm.org/citation.cfm?id=1080344&dl=ACM&coll=&CFID=15151515&CFTOKEN=6184618] ] etc.

One of the first steps to model the knowledge domain of a virtual community is to collect a vocabulary of domain-relevant terms, constituting the linguistic surface manifestation of domain concepts. Several methods to automatically extract technical terms from domain-specific document warehouses have been described in the literature. [ [http://lcl2.di.uniroma1.it/~sclano Sclano, F.] and [http://www.dsi.uniroma1.it/~velardi/welcome.htm Velardi, P.] . [http://lcl2.di.uniroma1.it/termextractor TermExtractor] : a Web Application to Learn the Shared Terminology of Emergent Web Communities. To appear in Proc. of the 3rd International Conference on Interoperability for Enterprise Software and Applications (I-ESA 2007). Funchal (Madeira Island), Portugal, March 28–30th, 2007.] [Navigli R. [http://www.dsi.uniroma1.it/~navigli/] and Velardi, P. (2004). "Learning Domain Ontologies from Document Warehouses and Dedicated Web Sites". Computational Linguistics. vol. 50 (2) [http://www.dsi.uniroma1.it/~navigli/pubs/CL_2004_Navigli_Velardi.pdf] ] [Wermter J. and Hahn U.: Finding New terminology in Very large Corpora, in Proc. of K-CAP'05, October 2-5, 2005, Banff, Alberta, Canada [http://portal.acm.org/citation.cfm?id=1088648] ] [Bourigault D. and Jacquemin C.: Term Extraction+Term Clustering: an integrated platform for computer-aided terminology, in Proc. of EACL , 1999 [http://acl.ldc.upenn.edu/E/E99/E99-1003.pdf] ] [Collier N., Nobata C. and Tsujii J. : Automatic acquisition and classification of terminology using a tagged corpus in the molecular biology domain, Terminology, 7(2). 239-257, 2002 [http://research.nii.ac.jp/~collier/papers/Terminology.pdf] ] [L. Kozakov, Y. Park, T. Fin, Y. Drissi, Y. Doganata, and T. Cofino "Glossary extraction and utilization in the information search and delivery system for IBM Technical Support", IBM System Journal, Volume 43, Number 3, 2004 [http://www.research.ibm.com/journal/sj/433/kozakov.pdf] ] [Y. Park, R. J. Byrd, B. Boguraev "Automatic glossary extraction: beyond terminology identification" International Conference On Computational Linguistics, Proceedings of the 19th international conference on Computational linguistics - Taipei, Taiwan, 2002 [http://portal.acm.org/citation.cfm?id=1072370&dl=ACM&coll=&CFID=15151515&CFTOKEN=6184618] ]

Typically, approaches to automatic term extraction make use of linguistic processors (part of speech tagging, phrase chunking) to extract terminological candidates, i.e. syntactically plausible terminological noun phrases, NPs (e.g. compounds "credit card", adjective-NPs "local tourist information office", and prepositional-NPs "board of directors" - in English, the first two constructs are the most frequent). Terminological entries are then filtered from the candidate list using statistical and machine learning methods. Once filtered, because of their low ambiguity and high specificity, these terms are particularly useful for conceptualizing a knowledge domain or for supporting the creation of a domain ontology. Furthermore, terminology extraction is a very useful starting point for semantic similarity, knowledge management, human translation and machine translation, etc.

ee also

*Information extraction
*Computational linguistics
*Natural language processing
*Domain Ontology
*Taxonomy
*Glossary
*Text simplification
*Text mining

References

External links

* [http://www-306.ibm.com/software/globalization/topics/terminology/introduction.jsp Introduction to terminology management] , by IBM
* [http://lcl2.di.uniroma1.it/termextractor TermExtractor] , a free terminology extraction web application
* [http://labs.translated.net/terminology-extraction/ TermFinder] , free online terminology extractor web application
* [http://www.termserver.eu/cms/content/view/14/28/ Statistical Bilingual Terminology Extractor] , online terminology extractor web application
* [http://ngram.sourceforge.net Ngram Statistics Package] , open source package for identifying collocations
* [http://www.termextractor.com Bilingual Terminology Extraction from Translation Memory files] , by Masterin, online and free, supports English, Swedish and Finnish (all language pairs and translation directions) web application
* [http://www.blogscope.net//tools/phrase.jsp English Phrases Extractor] , by the Blogscope team at the [http://www.cs.toronto.edu University of Toronto] , extracted terms are used to search for conceptually related blogs over the web rather than for linguistic analysis purpose web application