Una Nueva Técnica de Construcción de Grafos Semánticos para la Desambiguación Bilingüe del Sentido de las Palabras

  1. Duque Fernández, Andrés
  2. Araujo, Lourdes
  3. Martínez Romo, Juan
Journal:
Procesamiento del lenguaje natural

ISSN: 1135-5948

Year of publication: 2013

Issue: 51

Pages: 187-194

Type: Article

More publications in: Procesamiento del lenguaje natural

Sustainable development goals

info

SDG classification obtained using Aurora SDG artificial intelligence model.

Abstract

In this paper we present preliminary results obtained by the application of a new technique for building semantic graphs to the task of cross-lingual word sense disambigua- tion. Through the use of this unsupervised technique, we induce the senses associated with the translations of the ambiguous word in the target language. For this purpose, we use the translation of the words in the context of the ambiguous word in the source language to se- lect the most likely sense. The system has been evaluated on a dataset from a cross-lingual word sense disambiguation task proposed in the SemEval-2010 competition, outperforming all unsupervised systems participating in that task.

Bibliographic References

  • Agirre, Eneko, David Martínez, Oier Lopez de Lacalle, y Aitor Soroa. 2006. Two graphbased algorithms for state-of-the-art wsd. En EMNLP, paginas 585–593. ´
  • Agirre, Eneko y Aitor Soroa. 2007. Ubc-as: A graph based unsupervised system for induction and lassification. En Proceedings of the Fourth International Workshop on Semantic Evaluations (SemEval-2007), paginas 346–349, Prague, Czech Republic, June. Association for Computational Linguistics.
  • Banea, Carmen y Rada Mihalcea. 2011. Word sense disambiguation with multilingual features. En Proceedings of the Ninth International Conference on Computational Semantics, IWCS ’11, paginas 25–34. Association ´ for Computational Linguistics.
  • Diab, Mona T. y Philip Resnik. 2002. An unsupervised method for word sense tagging using parallel corpora. En ACL, paginas 255–262. ´
  • Fernandez-Ordonez, Erwin, Rada Mihalcea, y Samer Hassan. 2012. Unsupervised word sense disambiguation with multilingual representations. En LREC, paginas 847–851. ´
  • Guo, Weiwei y Mona Diab. 2010. Coleur and colslm: A wsd approach to multilingual lexical substitution, tasks 2 and 3 semeval 2010. En Proceedings of the 5th International Workshop on Semantic Evaluation, SemEval ’10, paginas 129–133, Strouds-burg, PA, USA. Association for Computational Linguistics.
  • Ide, Nancy y Jean Veronis. 1998. Word sense disambiguation: The state of the art. Computational Linguistics, 24:1–40.
  • Klapaftis, Ioannis P. y Suresh Manandhar. 2008. Word sense induction using graphs of collocations. En Proceeding of the 2008 conference on ECAI 2008, paginas 298–302, Amsterdam, The Netherlands, The Netherlands. IOS Press.
  • Koehn, Philipp. 2005. Europarl: A parallel corpus for statistical machine translation. En MT summit, volumen 5.
  • Lefever, Els y Veronique Hoste. 2010. Semeval2010 task 3: Cross-lingual word sense disambiguation. En Proceedings of the 5th International Workshop on Semantic Evaluation, SemEval ’10, paginas 15–20, Stroudsburg, PA, USA. Association for Computational Linguistics.
  • Lopez-Ostenero, Fernando. 2002. ´ Un sistema interactivo para la busqueda de informacion en idiomas desconocidos por el usuario. Ph.D. tesis, Departamento de Lenguajes y Sistemas Informaticos, Universidad Nacional de Educacion a Distancia. ´
  • Marquez, Lluís, Gerard Exsudero, David Martínez, y German Rigau. 2006. Supervised corpus-based methods for wsd. En Word Sense Disambiguation: Algorithms and Applications, volumen 33 de Text, Speech and Language Technology. Springer, Dordrecht, The Netherlands, paginas 167–216. ´
  • Martinez-Romo, Juan, Lourdes Araujo, Javier Borge-Holthoefer, Alex Arenas, Jose A. Capitan, y José A. Cuesta. 2011. Disentangling categorical relationships through a graph of co-occurrences. Phys. Rev. E, 84:046108, Oct.
  • Mihalcea, Rada. 2006. Knowledge-based methods for wsd. En Word Sense Disambiguation: Algorithms and Applications, volumen 33 de Text, Speech and Language Technology. Springer, Dordrecht, The Netherlands, paginas 107–132. ´
  • Ng, Hwee Tou, Bin Wang, y Yee Seng Chan. 2003. Exploiting parallel texts for word sense disambiguation: An empirical study. En ACL, paginas 455–462.
  • Pedersen, Ted. 2006. Unsupervised corpusbased methods for WSD. En Word Sense Disambiguation: Algorithms and Applications. Springer, paginas 133–166. ´
  • Pons, P. y M. Latapy. 2005. Computing communities in large networks using random walks. Lect. Notes Comput. Sci., 3733:284.
  • Resnik, Philip. 2004. Exploiting hidden meanings: Using bilingual text for monolingual annotation. En Int. Conf. Computational Linguistics and Intelligent Text Processing (CICLing), paginas 283–299. ´
  • Resnik, Philip y David Yarowsky. 1999. Distinguishing systems and distinguishing senses: new evaluation methods for word sense disambiguation. Natural Language Engineering, 5(2):113–133.
  • Schmid, Helmut. 1994. Probabilistic part-ofspeech tagging using decision trees. En Proceedings of international conference on new methods in language processing, volumen 12, paginas 44–49. Manchester, UK. ´ Silberer, Carina y Simone Paolo Ponzetto. 2010. Uhd: Cross-lingual word sense disambiguation using multilingual co-occurrence graphs. En Proceedings of the 5th International Workshop on Semantic Evaluation, SemEval’10, paginas 134–137, Stroudsburg, PA, USA. Association for Computational Linguistics.
  • van Gompel, Maarten. 2010. Uvt-wsd1: A cross-lingual word sense disambiguation system. En Proceedings of the 5th International Workshop on Semantic Evaluation, SemEval’10, paginas 238–241, Stroudsburg, PA, USA. ´ Association for Computational Linguistics.
  • Veronis, Jean. 2004. Hyperlex: lexical cartography for information retrieval. Computer Speech & Language, 18(3):223–252.
  • Vilarino, Darnes, Carlos Balderas, David Pinto, ˜Miguel Rodr´ıguez, y Saul Leon. 2010. Fcc: Modeling probabilities with giza++ for task #2 and #3 of semeval-2. En Proceedings of the 5th International Workshop on Semantic Evaluation, SemEval ’10, paginas 112–116, Stroudsburg, PA, USA. Association for Computational Linguistics.