Summary of the paper
| Title | A Contrastive Approach to Multi-word Extraction from Domain-specific Corpora |
|---|---|
| Authors | Francesca Bonin, Felice Dell'Orletta, Simonetta Montemagni and Giulia Venturi |
| Abstract | In this paper, we present a novel approach to multi-word terminology extractioncombining a well-known automatic term recognition approach, the C--NC valuemethod, with a contrastive ranking technique, aimed at refining obtainedresults either by filtering noise due to common words or by discerning betweensemantically different types of terms within heterogeneous terminologies.Differently from other contrastive methods proposed in the literature thatfocus on single terms to overcome the multi-word terms' sparsity problem, theproposed contrastive function is able to handle variation in low frequencyevents by directly operating on pre-selected multi-word terms. This methodologyhas been tested in two case studies carried out in the History of Art and Legaldomains. Evaluation of achieved results showed that the proposed two--stageapproach improves significantly multi--word term extraction results. Inparticular, for what concerns the legal domain it provides an answer to awell-known problem in the semi--automatic construction of legal ontologies,namely that of singling out law terms from terms of the specific domain beingregulated. |
| Language | Multilinguality |
| Topics | Ontologies, Tools, systems, applications, Multilinguality |
Full paper  |
A Contrastive Approach to Multi-word Extraction from Domain-specific Corpora |
| Bibtex | @InProceedings{BONIN10.553, author = {Francesca Bonin, Felice Dell'Orletta, Simonetta Montemagni and Giulia Venturi}, title = {A Contrastive Approach to Multi-word Extraction from Domain-specific Corpora}, 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} } |