Combining statistical and semantic approaches to the translation of ontologies and taxonomies

McCrae, J.; Montiel-Ponsoda, Elena; Aguado de Cea, G.; Espinoza Mejía, Mauricio y Cimiano, Philipp (2011). Combining statistical and semantic approaches to the translation of ontologies and taxonomies. En: "SSST-5, Fifth Workshop on Syntax, Semantics and Structure in Statistical Translation", 23/06/2011 - 23/06/2011, Portland, Oregon, USA. ISBN 978-1-932432-99-2. pp. 116-125.

Descripción

Título: Combining statistical and semantic approaches to the translation of ontologies and taxonomies
Autor/es:
  • McCrae, J.
  • Montiel-Ponsoda, Elena
  • Aguado de Cea, G.
  • Espinoza Mejía, Mauricio
  • Cimiano, Philipp
Tipo de Documento: Ponencia en Congreso o Jornada (Artículo)
Título del Evento: SSST-5, Fifth Workshop on Syntax, Semantics and Structure in Statistical Translation
Fechas del Evento: 23/06/2011 - 23/06/2011
Lugar del Evento: Portland, Oregon, USA
Título del Libro: Proceedings of SSST-5, Fifth Workshop on Syntax, Semantics and Structure in Statistical Translation
Fecha: 2011
ISBN: 978-1-932432-99-2
Materias:
Escuela: Facultad de Informática (UPM) [antigua denominación]
Departamento: Lingüistica Aplicada a la Ciencia y a la Tecnología
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (186kB) | Vista Previa

Resumen

Ontologies and taxonomies are widely used to organize concepts providing the basis for activities such as indexing, and as background knowledge for NLP tasks. As such, translation of these resources would prove useful to adapt these systems to new languages. However, we show that the nature of these resources is significantly different from the "free-text" paradigm used to train most statistical machine translation systems. In particular, we see significant differences in the linguistic nature of these resources and such resources have rich additional semantics. We demonstrate that as a result of these linguistic differences, standard SMT methods, in particular evaluation metrics, can produce poor performance. We then look to the task of leveraging these semantics for translation, which we approach in three ways: by adapting the translation system to the domain of the resource; by examining if semantics can help to predict the syntactic structure used in translation; and by evaluating if we can use existing translated taxonomies to disambiguate translations. We present some early results from these experiments, which shed light on the degree of success we may have with each approach

Más información

ID de Registro: 13368
Identificador DC: http://oa.upm.es/13368/
Identificador OAI: oai:oa.upm.es:13368
URL Oficial: http://dl.acm.org/citation.cfm?id=2024274
Depositado por: Memoria Investigacion
Depositado el: 24 Oct 2012 10:15
Ultima Modificación: 21 Abr 2016 12:41
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • e-ciencia
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM