This HTML5 document contains 45 embedded RDF statements represented using HTML+Microdata notation.

The embedded RDF content will be recognized by any processor of HTML5 Microdata.

Namespace Prefixes

PrefixIRI
dctermshttp://purl.org/dc/terms/
n20http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F00216208%3A11320%2F13%3A10194815%21RIV14-GA0-11320___/
n16http://localhost/temp/predkladatel/
n19http://linked.opendata.cz/resource/domain/vavai/projekt/
n4http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n9http://linked.opendata.cz/resource/domain/vavai/subjekt/
n8http://linked.opendata.cz/ontology/domain/vavai/
shttp://schema.org/
rdfshttp://www.w3.org/2000/01/rdf-schema#
skoshttp://www.w3.org/2004/02/skos/core#
n3http://linked.opendata.cz/ontology/domain/vavai/riv/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n5http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n17http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n15http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n12http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n14http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n6http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n18http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F00216208%3A11320%2F13%3A10194815%21RIV14-GA0-11320___
rdf:type
skos:Concept n8:Vysledek
rdfs:seeAlso
http://www.springer.com/computer/database+management+%26+information+retrieval/book/978-3-642-37255-1
dcterms: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 %22semi-automatic%22 exploration of the space in several directions and evaluate the obtained systems. 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 %22semi-automatic%22 exploration of the space in several directions and evaluate the obtained systems.
dcterms:title
No Free Lunch in Factored Phrase-Based Machine Translation No Free Lunch in Factored Phrase-Based Machine Translation
skos:prefLabel
No Free Lunch in Factored Phrase-Based Machine Translation No Free Lunch in Factored Phrase-Based Machine Translation
skos:notation
RIV/00216208:11320/13:10194815!RIV14-GA0-11320___
n8:predkladatel
n9:orjk%3A11320
n3:aktivita
n15:P
n3:aktivity
P(GAP406/11/1499)
n3:cisloPeriodika
1
n3:dodaniDat
n18:2014
n3:domaciTvurceVysledku
n4:2630176 n4:3528839
n3:druhVysledku
n14:J
n3:duvernostUdaju
n17:S
n3:entitaPredkladatele
n20:predkladatel
n3:idSjednocenehoVysledku
91859
n3:idVysledku
RIV/00216208:11320/13:10194815
n3:jazykVysledku
n12:eng
n3:klicovaSlova
translation; machine; based; phrase; factored; lunch; free
n3:klicoveSlovo
n5:lunch n5:based n5:free n5:phrase n5:factored n5:machine n5:translation
n3:kodStatuVydavatele
GB - Spojené království Velké Británie a Severního Irska
n3:kontrolniKodProRIV
[273549D9E6D8]
n3:nazevZdroje
Lecture Notes in Computer Science
n3:obor
n6:AI
n3:pocetDomacichTvurcuVysledku
2
n3:pocetTvurcuVysledku
2
n3:projekt
n19:GAP406%2F11%2F1499
n3:rokUplatneniVysledku
n18:2013
n3:svazekPeriodika
7817
n3:tvurceVysledku
Bojar, Ondřej Tamchyna, Aleš
s:issn
0302-9743
s:numberOfPages
14
n16:organizacniJednotka
11320