Maximum Entropy Translation Model in Dependency-Based MT Framework
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F10%3A10078023" target="_blank" >RIV/00216208:11320/10:10078023 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Maximum Entropy Translation Model in Dependency-Based MT Framework
Original language description
Maximum Entropy Principle has been used successfully in various NLP tasks. In this paper we propose a forward translation model consisting of a set of maximum entropy classifiers: a separate classifier is trained for each (sufficiently frequent) source-side lemma. In this way the estimates of translation probabilities can be sensitive to a large number of features derived from the source sentence (including non-local features, features making use of sentence syntactic structure, etc.). When integrated into English-to- Czech dependency-based translation scenario implemented in the TectoMT framework, the new translation model significantly outperforms the baseline model (MLE) in terms of BLEU. The performance is further boosted in a configuration inspired by Hidden Tree Markov Models which combines the maximum entropy translation model with the target-language dependency tree model.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
AI - Linguistics
OECD FORD branch
—
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2010
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 Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
ISBN
978-1-932432-71-8
ISSN
—
e-ISSN
—
Number of pages
1
Pages from-to
—
Publisher name
Association for Computational Linguistics
Place of publication
Uppsala, Sweden
Event location
Uppsala, Sweden
Event date
Jul 15, 2010
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—