Machine Translation with Many Manually Labeled Discourse Connectives

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F13%3A10194660" target="_blank" >RIV/00216208:11320/13:10194660 - isvavai.cz</a>
Result on the web
<a href="http://www.aclweb.org/anthology/W/W13/W13-3306.pdf" target="_blank" >http://www.aclweb.org/anthology/W/W13/W13-3306.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Machine Translation with Many Manually Labeled Discourse Connectives
Original language description
The paper presents machine translation experiments from English to Czech with a large amount of manually annotated discourse connectives. The gold-standard discourse relation annotation leads to better translation performance in ranges of 4-60% for someambiguous English connectives and helps to find correct syntactical constructs in Czech for less ambiguous connectives. Automatic scoring confirms the stability of the newly built discourseaware translation systems. Error analysis and human translation evaluation point to the cases where the annotation was most and where less helpful.
Czech name
—
Czech description
—

Project
<a href="/en/project/GAP406%2F12%2F0658" target="_blank" >GAP406/12/0658: Coreference, discourse relations and information structure in a contrastive perspective</a><br>
Continuities
S - Specificky vyzkum na vysokych skolach

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
51st Annual Meeting of the Association for Computational Linguistics Proceedings of the Workshop on Discourse in Machine Translation
ISBN
978-1-937284-68-8
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
43-50
Publisher name
Omnipress, Inc.
Place of publication
Sofija, Bulgaria
Event location
Sofija, Bulgaria
Event date
Aug 9, 2013
Type of event by nationality
CST - Celostátní akce
UT code for WoS article
—

Similar results(10)