No Free Lunch in Factored Phrase-Based Machine Translation

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F13%3A10194815" target="_blank" >RIV/00216208:11320/13:10194815 - isvavai.cz</a>
Result on the web
<a href="http://www.springer.com/computer/database+management+%26+information+retrieval/book/978-3-642-37255-1" target="_blank" >http://www.springer.com/computer/database+management+%26+information+retrieval/book/978-3-642-37255-1</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
No Free Lunch in Factored Phrase-Based Machine Translation
Original language description
Factored models have been successfully used in many language pairs to improve translation quality in various aspects. In this work, we analyze this paradigm in an attempt at automating the search for well-performing machine translation systems. We examine the space of possible factored systems, concluding that a fully automatic search for good configurations is not feasible. We demonstrate that even if results of automatic evaluation are available, guiding the search is difficult due to small differences between systems, which are further blurred by randomness in tuning. We describe a heuristic for estimating the complexity of factored models. Finally, we discuss the possibilities of a "semi-automatic" exploration of the space in several directions andevaluate the obtained systems.
Czech name
—
Czech description
—

Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
AI - Linguistics
OECD FORD branch
—

Project
<a href="/en/project/GAP406%2F11%2F1499" target="_blank" >GAP406/11/1499: Czech in the Machine Translation Era (CZECHMATE)</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

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

Similar results(10)