Publishing Partner: Cambridge University Press CUP Extra Wiley-Blackwell Publisher Login
amazon logo
More Info


New from Oxford University Press!

ad

Latin: A Linguistic Introduction

By Renato Oniga and Norma Shifano

Applies the principles of contemporary linguistics to the study of Latin and provides clear explanations of grammatical rules alongside diagrams to illustrate complex structures.


New from Cambridge University Press!

ad

The Ancient Language, and the Dialect of Cornwall, with an Enlarged Glossary of Cornish Provincial Words

By Frederick W.P. Jago

Containing around 3,700 dialect words from both Cornish and English,, this glossary was published in 1882 by Frederick W. P. Jago (1817–92) in an effort to describe and preserve the dialect as it too declined and it is an invaluable record of a disappearing dialect and way of life.


New from Brill!

ad

Linguistic Bibliography for the Year 2013

The Linguistic Bibliography is by far the most comprehensive bibliographic reference work in the field. This volume contains up-to-date and extensive indexes of names, languages, and subjects.


Academic Paper


Title: Learning Morphology with Morfette
Paper URL: http://www.lrec-conf.org/proceedings/lrec2008/pdf/594_paper.pdf
Author: Grzegorz Chrupała
Email: click here to access email
Homepage: http://www.lsv.uni-saarland.de/personalPages/gchrupala/index.html
Institution: Saarland University
Author: Georgiana Dinu
Email: click here to access email
Institution: Saarland University
Author: Josef Van Genabith
Email: click here to access email
Institution: Dublin City University
Linguistic Field: Computational Linguistics
Abstract: Morfette is a modular, data-driven, probabilistic system which learns to perform joint morphological tagging and lemmatization from morphologically annotated corpora. The system is composed of two learning modules which are trained to predict morphological tags and lemmas using the Maximum Entropy classifier. The third module dynamically combines the predictions of the Maximum-Entropy models and outputs a probability distribution over tag-lemma pair sequences. The lemmatization module exploits the idea of recasting lemmatization as a classification task by using class labels which encode mappings from word forms to lemmas. Experimental evaluation results and error analysis on three morphologically rich languages show that the system achieves high accuracy with no language-specific feature engineering or additional resources.
Type: Individual Paper
Status: Completed
Venue: LREC 2008
URL: http://www.lrec-conf.org/proceedings/lrec2008/pdf/594_paper.pdf


Back
Add a new paper
Return to Academic Papers main page
Return to Directory of Linguists main page