PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Morpho Challenge - evaluation of algorithms for unsupervised learning of morphology in various tasks and languages
Mikko Kurimo, Sami Virpioja, Ville Turunen and Teemu Hirsimäki
In: 2009 Annual Conference of the North american Chapter of the association for Computational Linguistics, NAACL 2009(2009).

Abstract

After the release of the open sou rce softw are implementation of M orfessor alg orithm, a se- ries of several open evalu ations has b een or- g aniz ed for u nsu pervised morpheme analy - sis and morpheme-b ased speech recog nition and information retrieval. T he u nsu pervised morpheme analy sis is a particu larly attrac- tive approach for speech and lang u ag e tech- nolog y for the morpholog ically complex lan- g u ag es. W hen the amou nt of distinct w ord forms b ecomes prohib itive for the constru c- tion of a su f cient lex icon, it is important that the w ords can b e seg mented into smaller meaning fu l lang u ag e modeling u nits. In this presentation w e w ill demonstrate the resu lts of the evalu ations, the b aseline sy stems b u ilt u sing the open sou rce tools, and invite re- search g rou ps to participate in the nex t eval- u ation w here the task is to enhance statistical machine translation b y morpheme analy sis.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Natural Language Processing
Speech
Information Retrieval & Textual Information Access
ID Code:6054
Deposited By:Mikko Kurimo
Deposited On:08 March 2010