About: Maximum Entropy Translation Model in Dependency-Based MT Framework     Goto   Sponge   NotDistinct   Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

AttributesValues
rdf:type
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.
  • 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. (en)
Title
  • Maximum Entropy Translation Model in Dependency-Based MT Framework
  • Maximum Entropy Translation Model in Dependency-Based MT Framework (en)
skos:prefLabel
  • Maximum Entropy Translation Model in Dependency-Based MT Framework
  • Maximum Entropy Translation Model in Dependency-Based MT Framework (en)
skos:notation
  • RIV/00216208:11320/10:10078023!RIV11-GA0-11320___
http://linked.open...avai/riv/aktivita
http://linked.open...avai/riv/aktivity
  • P(GD201/09/H057), P(LC536), S, Z(MSM0021620838)
http://linked.open...vai/riv/dodaniDat
http://linked.open...aciTvurceVysledku
http://linked.open.../riv/druhVysledku
http://linked.open...iv/duvernostUdaju
http://linked.open...titaPredkladatele
http://linked.open...dnocenehoVysledku
  • 269950
http://linked.open...ai/riv/idVysledku
  • RIV/00216208:11320/10:10078023
http://linked.open...riv/jazykVysledku
http://linked.open.../riv/klicovaSlova
  • framework; based; dependency; model; translation; entropy; maximum (en)
http://linked.open.../riv/klicoveSlovo
http://linked.open...ontrolniKodProRIV
  • [7E2EB7CD7B47]
http://linked.open...v/mistoKonaniAkce
  • Uppsala, Sweden
http://linked.open...i/riv/mistoVydani
  • Uppsala, Sweden
http://linked.open...i/riv/nazevZdroje
  • Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
http://linked.open...in/vavai/riv/obor
http://linked.open...ichTvurcuVysledku
http://linked.open...cetTvurcuVysledku
http://linked.open...vavai/riv/projekt
http://linked.open...UplatneniVysledku
http://linked.open...iv/tvurceVysledku
  • Mareček, David
  • Popel, Martin
  • Žabokrtský, Zdeněk
http://linked.open...vavai/riv/typAkce
http://linked.open.../riv/zahajeniAkce
http://linked.open...n/vavai/riv/zamer
number of pages
http://purl.org/ne...btex#hasPublisher
  • Association for Computational Linguistics
https://schema.org/isbn
  • 978-1-932432-71-8
http://localhost/t...ganizacniJednotka
  • 11320
is http://linked.open...avai/riv/vysledek of
Faceted Search & Find service v1.16.118 as of Jun 21 2024


Alternative Linked Data Documents: ODE     Content Formats:   [cxml] [csv]     RDF   [text] [turtle] [ld+json] [rdf+json] [rdf+xml]     ODATA   [atom+xml] [odata+json]     Microdata   [microdata+json] [html]    About   
This material is Open Knowledge   W3C Semantic Web Technology [RDF Data] Valid XHTML + RDFa
OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 58 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software