Type

Conference Proceedings

Authors

Josef van Genabith
Lamia Tounsi
Joseph Le Roux
Deirdre Hogan
Jennifer Foster
Mohammed Attia

Subjects

Linguistics

Topics
arabic french classification machine translating statistical parsing english art languages

Handling unknown words in statistical latent-variable parsing models for Arabic, English and French (2010)

Abstract This paper presents a study of the impact of using simple and complex morphological clues to improve the classification of rare and unknown words for parsing. We compare this approach to a language-independent technique often used in parsers which is based solely on word frequencies. This study is applied to three languages that exhibit different levels of morphological expressiveness: Arabic, French and English. We integrate information about Arabic affixes and morphotactics into a PCFG-LA parser and obtain stateof-the-art accuracy. We also show that these morphological clues can be learnt automatically from an annotated corpus.
Collections Ireland -> Dublin City University -> Publication Type = Conference or Workshop Item
Ireland -> Dublin City University -> DCU Faculties and Centres = DCU Faculties and Schools: Faculty of Engineering and Computing: School of Computing
Ireland -> Dublin City University -> Subject = Computer Science
Ireland -> Dublin City University -> DCU Faculties and Centres = DCU Faculties and Schools
Ireland -> Dublin City University -> Status = Published
Ireland -> Dublin City University -> Subject = Computer Science: Machine translating
Ireland -> Dublin City University -> DCU Faculties and Centres = Research Initiatives and Centres: National Centre for Language Technology (NCLT)
Ireland -> Dublin City University -> DCU Faculties and Centres = DCU Faculties and Schools: Faculty of Engineering and Computing
Ireland -> Dublin City University -> DCU Faculties and Centres = Research Initiatives and Centres

Full list of authors on original publication

Josef van Genabith, Lamia Tounsi, Joseph Le Roux, Deirdre Hogan, Jennifer Foster, Mohammed Attia

Experts in our system

1
Deirdre Hogan
Dublin City University
Total Publications: 14
 
2
Jennifer Foster
Dublin City University
Total Publications: 53