<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=undefined&type=result"></script>');
-->
</script>

COPY SCRIPT

For further information contact us at helpdesk@openaire.eu

Linguistic Structure in Statistical Machine Translation

Name: Linguistic Structure in Statistical Machine Translation
Creator: Herrmann, Teresa
Keywords: ddc:004, Translation, Machine, DATA processing & computer science, Structure, Statistical, Linguistic, 410, info:eu-repo/classification/ddc/004, 400

descriptionPublicationkeyboard_double_arrow_right Doctoral thesis , Other literature type 01 Jan 2015 Germany Publisher:Karlsruhe

Authors: Herrmann, Teresa;

doi: 10.5445/ir/1000054573

Linguistic Structure in Statistical Machine Translation

- Summary
- Subjects
- Metrics

Abstract

This thesis investigates the influence of linguistic structure in statistical machine translation. We develop a word reordering model based on syntactic parse trees and address the issues of pronouns and morphological agreement with a source discriminative word lexicon predicting the translation for individual words using structural features. When used in phrase-based machine translation, the models improve the translation for language pairs with different word order and morphological variation.

Country

Germany

Related Organizations

Karlsruhe Institute of Technology
Germany

Keywords

ddc:004, Translation, Machine, DATA processing & computer science, Structure, Statistical, Linguistic, 410, info:eu-repo/classification/ddc/004, 400, 004

Impact byBIP!

	citations This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	2
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average

Found an issue? Give us feedback

Average

Green