Header

UZH-Logo

Maintenance Infos

Automatic phrase alignment. Using statistical n-gram alignment for syntactic phrase alignment


Samuelsson, Y; Volk, M (2007). Automatic phrase alignment. Using statistical n-gram alignment for syntactic phrase alignment. In: 6th Workshop on Treebanks and Linguistic Theories, Bergen, 2007 - 2007.

Abstract

A parallel treebank consists of syntactically annotated sentences in two or more languages, taken from translated documents. These parallel sentences are linked through alignment. This paper explores the use of word n-gram alignment, computed for statistical machine translation, to create syntactic phrase alignment. We achieve a weighted
F0.5 -score of over 65%.

Abstract

A parallel treebank consists of syntactically annotated sentences in two or more languages, taken from translated documents. These parallel sentences are linked through alignment. This paper explores the use of word n-gram alignment, computed for statistical machine translation, to create syntactic phrase alignment. We achieve a weighted
F0.5 -score of over 65%.

Statistics

Downloads

206 downloads since deposited on 31 Aug 2009
27 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Language:English
Event End Date:2007
Deposited On:31 Aug 2009 12:36
Last Modified:11 Aug 2017 06:03

Download

Download PDF  'Automatic phrase alignment. Using statistical n-gram alignment for syntactic phrase alignment'.
Preview
Filetype: PDF
Size: 1MB