Comparison of Coreference Resolvers for Deep Syntax Translation
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F15%3A10318150" target="_blank" >RIV/00216208:11320/15:10318150 - isvavai.cz</a>
Result on the web
<a href="http://aclweb.org/anthology/W15-2502" target="_blank" >http://aclweb.org/anthology/W15-2502</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Comparison of Coreference Resolvers for Deep Syntax Translation
Original language description
This work focuses on using anaphora for machine translation with deep-syntactic transfer. We compare multiple coreference resolvers for English in terms of how they affect the quality of pronoun translation in English-Czech and English-Dutch machine translation systems with deep transfer. We examine which pronouns in the target language depend on anaphoric information, and design rules that take advantage of this information. The resolvers' performance measured by translation quality is contrasted withtheir intrinsic evaluation results. In addition, a more detailed manual analysis of English-to-Czech translation was carried out.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the Second Workshop on Discourse in Machine Translation
ISBN
978-1-941643-32-7
ISSN
—
e-ISSN
—
Number of pages
7
Pages from-to
17-23
Publisher name
Association for Computational Linguistics
Place of publication
Lisboa, Portugal
Event location
Lisboa, Portugal
Event date
Sep 17, 2015
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—