Building a Spanish lexicon for corpus analysis

Jiménez, Ricardo-María and Sanjurjo-González, Hugo and Rayson, Paul Edward and Piao, Scott Songlin (2017) Building a Spanish lexicon for corpus analysis. In: Languages at the Crossroads : Training, Accreditation and Context of Use : 35th Edition of the International Conference of the Spanish Association of Applied Linguistics. Universidad de Jaén, ESP, pp. 227-236. ISBN 9788491591085

[thumbnail of Final_AESLA-2017]
Preview
PDF (Final_AESLA-2017)
Final_AESLA_2017.pdf - Accepted Version

Download (251kB)

Abstract

This paper seeks to describe the creation of a Spanish lexicon with semantic annotation in order to analyse more extensive corpora in the Spanish language. The semantic resources most employed nowadays are WordNet, FrameNet, PDEV and USAS, but they have been used mainly for English language research. The creation of a large Spanish lexicon will permit a greater amount of studies of corpora in Spanish can be undertaken. In the description of the steps followed for the construction of the lexicon, the difficulties encountered in its creation, and the solutions used to overcome them will be described. Finally, the construction of the lexicon will allow specific research tasks to be carried out, such as metaphor analysis, ACD studies and even PLN studies.

Item Type:
Contribution in Book/Report/Proceedings
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1200/1203
Subjects:
?? spanish semantic lexiconsemantic annotation toolnatural language processinglanguage and linguisticsartificial intelligence ??
ID Code:
84729
Deposited By:
Deposited On:
16 Mar 2017 05:53
Refereed?:
Yes
Published?:
Published
Last Modified:
12 Oct 2024 00:39