Analysis of MultiWord Expression Translation Errors in Statistical Machine Translation

Natalia Klyueva; Jeevanthi  Liyanapathirana

Analysis of MultiWord Expression Translation Errors in Statistical Machine Translation

Natalia Klyueva, Jeevanthi Liyanapathirana

Charles University

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

Abstract

In this paper, we analyse the usage of multiword expressions (MWE) in Statistical Machine Translation (SMT). We exploit the Moses SMT toolkit to train models for French-English and Czech-Russian language pairs. For each language pair, two models were built: a baseline model without additional MWE data and the model enhanced with information on MWE. For the French-English pair, we tried three methods of introducing the MWE data. For Czech-Russian pair, we used just one method – adding automatically extracted data as a parallel corpus.

Originalsprog	Engelsk
Titel	Workshop Proceedings. Multi-Word Units in Machine Translation and Translation Technologies. MUMTTT 2015
Redaktører	Gloria Corpas Pastor, Johanna Monti, Violeta Seretan, Ruslan Mitkov
Udgivelsessted	Geneve
Forlag	Tradulex
Publikationsdato	2015
Sider	87-91
ISBN (Trykt)	9782970073697
Status	Udgivet - 2015
Begivenhed	The 2nd Workshop on Multi-word Units in Machine Translation and Translation Technology. MUMTTT 2015 : Part of EUROPHRAS 2015 - Malaga, Spanien Varighed: 1 jul. 2015 → 2 jul. 2015 Konferencens nummer: 2 http://typo.uni-konstanz.de/parseme/index.php/events/118-mumttt-workshop-at-europhras-15

Konference

Konference	The 2nd Workshop on Multi-word Units in Machine Translation and Translation Technology. MUMTTT 2015
Nummer	2
Land/Område	Spanien
By	Malaga
Periode	01/07/2015 → 02/07/2015
Internetadresse	http://typo.uni-konstanz.de/parseme/index.php/events/118-mumttt-workshop-at-europhras-15

Adgang til dokumentet

http://www.europhras2015.eu/workshopproceedings_def/!Licens: Ikke-specificeret

Handle.net

Persistent link

Citationsformater

@inproceedings{08d47a5702a24d1491ca63d76c3eb83a,

title = "Analysis of MultiWord Expression Translation Errors in Statistical Machine Translation",

abstract = "In this paper, we analyse the usage of multiword expressions (MWE) in Statistical Machine Translation (SMT). We exploit the Moses SMT toolkit to train models for French-English and Czech-Russian language pairs. For each language pair, two models were built: a baseline model without additional MWE data and the model enhanced with information on MWE. For the French-English pair, we tried three methods of introducing the MWE data. For Czech-Russian pair, we used just one method – adding automatically extracted data as a parallel corpus.",

author = "Natalia Klyueva and Jeevanthi Liyanapathirana",

year = "2015",

language = "English",

isbn = "9782970073697",

pages = "87--91",

editor = "Pastor, {Gloria Corpas} and Johanna Monti and Violeta Seretan and Ruslan Mitkov",

booktitle = "Workshop Proceedings. Multi-Word Units in Machine Translation and Translation Technologies. MUMTTT 2015",

publisher = "Tradulex",

address = "Switzerland",

note = "The 2nd Workshop on Multi-word Units in Machine Translation and Translation Technology. MUMTTT 2015 ; Conference date: 01-07-2015 Through 02-07-2015",

url = "http://typo.uni-konstanz.de/parseme/index.php/events/118-mumttt-workshop-at-europhras-15",

}

Klyueva, N & Liyanapathirana, J 2015, Analysis of MultiWord Expression Translation Errors in Statistical Machine Translation. i GC Pastor, J Monti, V Seretan & R Mitkov (red), Workshop Proceedings. Multi-Word Units in Machine Translation and Translation Technologies. MUMTTT 2015. Tradulex, Geneve, s. 87-91, The 2nd Workshop on Multi-word Units in Machine Translation and Translation Technology. MUMTTT 2015 , Malaga, Spanien, 01/07/2015. <http://www.europhras2015.eu/workshopproceedings_def/!>

Analysis of MultiWord Expression Translation Errors in Statistical Machine Translation. / Klyueva, Natalia; Liyanapathirana, Jeevanthi .
Workshop Proceedings. Multi-Word Units in Machine Translation and Translation Technologies. MUMTTT 2015. red. / Gloria Corpas Pastor; Johanna Monti; Violeta Seretan; Ruslan Mitkov. Geneve: Tradulex, 2015. s. 87-91.

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

TY - GEN

T1 - Analysis of MultiWord Expression Translation Errors in Statistical Machine Translation

AU - Klyueva, Natalia

AU - Liyanapathirana, Jeevanthi

N1 - Conference code: 2

PY - 2015

Y1 - 2015

N2 - In this paper, we analyse the usage of multiword expressions (MWE) in Statistical Machine Translation (SMT). We exploit the Moses SMT toolkit to train models for French-English and Czech-Russian language pairs. For each language pair, two models were built: a baseline model without additional MWE data and the model enhanced with information on MWE. For the French-English pair, we tried three methods of introducing the MWE data. For Czech-Russian pair, we used just one method – adding automatically extracted data as a parallel corpus.

AB - In this paper, we analyse the usage of multiword expressions (MWE) in Statistical Machine Translation (SMT). We exploit the Moses SMT toolkit to train models for French-English and Czech-Russian language pairs. For each language pair, two models were built: a baseline model without additional MWE data and the model enhanced with information on MWE. For the French-English pair, we tried three methods of introducing the MWE data. For Czech-Russian pair, we used just one method – adding automatically extracted data as a parallel corpus.

M3 - Article in proceedings

SN - 9782970073697

SP - 87

EP - 91

BT - Workshop Proceedings. Multi-Word Units in Machine Translation and Translation Technologies. MUMTTT 2015

A2 - Pastor, Gloria Corpas

A2 - Monti, Johanna

A2 - Seretan, Violeta

A2 - Mitkov, Ruslan

PB - Tradulex

CY - Geneve

T2 - The 2nd Workshop on Multi-word Units in Machine Translation and Translation Technology. MUMTTT 2015

Y2 - 1 July 2015 through 2 July 2015

ER -