Summary of the paper
| Title | GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains |
|---|---|
| Authors | Patrice Lopez and Laurent Romary |
| Abstract | The development of a multilingual terminology is a very long and costlyprocess. We present the creation of a multilingual terminological databasecalled GRISP covering multiple technical and scientific fields from variousopen resources. A crucial aspect is the merging of the different resources which is based inour proposal on the definition of a sound conceptual model, different domainmapping and the use of structural constraints and machine learning techniquesfor controlling the fusion process. The result is a massive terminologicaldatabase of several millions terms, concepts, semantic relations anddefinitions. The accuracy of the concept merging between several resources havebeen evaluated following several methods. This resource has allowed us to improve significantly the mean averageprecision of an information retrieval system applied to a large collection ofmultilingual and multidomain patent documents. New specialized terminologies,not specifically created for text processing applications, can be aggregatedand merged to GRISP with minimal manual efforts. |
| Language | Lexicon, lexical database |
| Topics | Controlled languages, Information Extraction, Information Retrieval, Lexicon, lexical database |
Full paper  |
GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains |
| Bibtex | @InProceedings{LOPEZ10.829, author = {Patrice Lopez and Laurent Romary}, title = {GRISP: A Massive Multilingual Terminological Database for Scientific and Technical Domains}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |