analysis of errors – Ixa Group. Language Technology.

Mitxelena Award for PhD theses: Maite Oronoz eta Larraitz Uria

Kepa Sarasola — Wed, 06 Apr 2011 11:46:22 +0000

Our colleague Maite Oronoz won last Monday the II. Koldo MItxelena Award for PhD Theses organized by Euskaltzaindia (the Academy of Basque Language) and the University of the Basque Country.

CONGRATULATIONS Maite!

Besides, our colleague Larraitz Uria’s PhD thesis was also nominated for this award.

Both theses face language error detection. Maite’s thesis deals with it from a computational point of view, while Larraitz’ work does it from a linguistic perspective.

Title of Maite’s thesis: Euskarazko errore sintaktikoak detektatzeko eta zuzentzeko baliabideen garapena: datak, postposizio-lokuzioak eta komunztadura.
(Saroi, a system to detect and correct syntactic mistakes: dates, complex postpositions, and agreement.)
Maite’s supervisors: Arantza Diaz de Ilarraza and Koldo Gojenola
Title of Larraitz’ thesis: Euskarazko erroreen eta desbideratzeen analisirako lan-ingurunea. Determinatzaile-erroreen azterketa eta prozesamendua.
(A framework for the analysis of errors and deviations in Basque texts. Analysis and processing of errors on the use of determiners.
Larraitz’ supervisors: Igone Zabala and Montse Maritxalar
Publications:

Maite Oronoz, Arantza Díaz de Ilarraza, Koldo Gojenola 2010
Design and evaluation of an agreement error detection system: testing the effect of ambiguity, parser and corpus type
7th International Conference on Natural Language Processing, IceTAL 2010, H. Loftsson, E. R ̈gnvaldsson, S. Helgad ́ttir (Eds.): IceTAL 2010, LNAI 6233, pp. 281–292, 2010. Springer-Verlag Berlin Heidelberg 2010, August 16-18, 2010 Reykjavik, Iceland
Díaz de Ilarraza A., Gojenola K., Oronoz M. 2009
Evaluating the Impact of Morphosyntactic Ambiguity in Grammatical Error Detection
Recent Advances in Natural Language Processing ISSN 1313-8502. Páginas: 155-160

Uria L. Arrieta B., Díaz de Ilarraza A., Maritxalar M., Oronoz M. 2009
Determiner errors in Basque: Analysis and Automatic Detection.
Proceedings de XXV Conferencia de la Sociedad Española para el Procesamiento del Lenguaje Natural (SEPLN), Revista nº 43, pp. 41-48 Septiembre 2009. ISSN: 1135-5948.

Larraitz Uria’s PhD Thesis: A framework for the analysis of errors and deviations in Basque texts. Analysis and processing of errors on the use of determiners.

Kepa Sarasola — Fri, 16 Apr 2010 18:01:18 +0000

We analyse errors and deviations made in Basque to bring contributions to two research fields: in the field of automatic error treatment, our aim is to develop spelling, grammar and style checkers for Basque; in the field of ICALL, we aim to create resources for the study of the language learning process. In both fields, in order to develop useful tools which consider the needs that real users might have, it is necessary to carry out a complete analysis of the errors and deviations made in Basque, taking also into account the sociolinguistic situation of our language community.

For that, in this dissertation we have developed a whole environment composed of those resources which are essential for error analysis: corpora (learner and native speaker corpora), an error editor tool called EtikErro, an error classification and two data-bases (named Errors and Learners) to store information related to the tagged examples. We have also defined the basic criterion for the analysis and processing of errors. As it is not possible to study all the error types at the same time, in this dissertation we have dealt with the analysis and automatic treatment of determiner-errors in Basque. We have written some rules that will be integrated in XUXENg, the grammar-checker we are developing for Basque.

ixa.si.ehu.es/Ixa/Argitalpenak/Tesiak/1260962506/publikoak/TESIA-Larraitz_2009

Maite Oronoz develops new system to detect and correct syntactic mistakes (2009/09/21)

Kepa Sarasola — Mon, 21 Sep 2009 17:51:39 +0000

The new system called Saroi is a general tool which, apart from dealing with errors, can be used to make consultations about syntactic structures in the trees of analysis and to make searches for linguistic structures in such trees.

Maite Oronoz has analysed the existing tools for the detection and correction of syntactic mistakes. To detect context errors such as concordance errors, it is necessary to analyse the tree structure of the sentences. The researcher did not find a suitable tool for this purpose so she created Saroi, which not only deals with mistakes in syntax but can also be used for consulting tree structure analyses and for carrying out searches for linguistic structures in such trees.