Type

Conference Proceedings

Authors

Josef van Genabith
Jennifer Foster
Anton Bryl
Ozlem Cetinoglu

Subjects

Linguistics

Topics
english statistical dependency labels datasets post editing dependency analysis machine translating parsing

Improving dependency label accuracy using statistical post-editing: A cross-framework study (2011)

Abstract We present a statistical post-editing method for modifying the dependency labels in a dependency analysis. We test the method using two English datasets, three parsing systems and three labelled dependency schemes. We demonstrate how it can be used both to improve dependency label accuracy in parser output and highlight problems with and differences between constituency-to-dependency conversions.
Collections Ireland -> Dublin City University -> Publication Type = Conference or Workshop Item
Ireland -> Dublin City University -> Subject = Computer Science
Ireland -> Dublin City University -> DCU Faculties and Centres = Research Initiatives and Centres: Centre for Next Generation Localisation (CNGL)
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 = Research Initiatives and Centres

Full list of authors on original publication

Josef van Genabith, Jennifer Foster, Anton Bryl, Ozlem Cetinoglu

Experts in our system

1
Jennifer Foster
Dublin City University
Total Publications: 53
 
2
Ozlem Cetinoglu
Dublin City University
Total Publications: 10