Tree Kernels for Machine Translation Quality Estimation

Christian Hardmeier; Joakim Nivre; Jörg Tiedemann

Tree Kernels for Machine Translation Quality Estimation

Christian Hardmeier
, Joakim Nivre
, Jörg Tiedemann

Uppsala University

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

This paper describes Uppsala University’s submissions to the Quality Estimation (QE) shared task at WMT 2012. We present a QE system based on Support Vector Machine regression, using a number of explicitly defined features extracted from the Machine Translation input, output and models in combination with tree kernels over constituency and dependency parse trees for the input and output sentences. We confirm earlier results suggesting that tree kernels can be a useful tool for QE system construction especially in the early stages of system design.

Original language	English
Title of host publication	Proceedings of the Seventh Workshop on Statistical Machine Translation
Publication date	8 Jun 2012
Pages	109–113
ISBN (Print)	978-1-937284-20-6
Publication status	Published - 8 Jun 2012
Externally published	Yes

Keywords

Quality Estimation
Machine Translation
Support Vector Regression
Tree Kernels
Parse Trees

Access to Document

https://aclanthology.org/W12-3112.pdf

Cite this

@inproceedings{deae5d6ab05947539d73f01d23c77dd2,

title = "Tree Kernels for Machine Translation Quality Estimation",

abstract = "This paper describes Uppsala University{\textquoteright}s submissions to the Quality Estimation (QE) shared task at WMT 2012. We present a QE system based on Support Vector Machine regression, using a number of explicitly defined features extracted from the Machine Translation input, output and models in combination with tree kernels over constituency and dependency parse trees for the input and output sentences. We confirm earlier results suggesting that tree kernels can be a useful tool for QE system construction especially in the early stages of system design.",

keywords = "Quality Estimation, Machine Translation, Support Vector Regression, Tree Kernels, Parse Trees",

author = "Christian Hardmeier and Joakim Nivre and J{\"o}rg Tiedemann",

year = "2012",

month = jun,

day = "8",

language = "English",

isbn = "978-1-937284-20-6",

pages = "109–113",

booktitle = "Proceedings of the Seventh Workshop on Statistical Machine Translation",

}

TY - GEN

T1 - Tree Kernels for Machine Translation Quality Estimation

AU - Hardmeier, Christian

AU - Nivre, Joakim

AU - Tiedemann, Jörg

PY - 2012/6/8

Y1 - 2012/6/8

N2 - This paper describes Uppsala University’s submissions to the Quality Estimation (QE) shared task at WMT 2012. We present a QE system based on Support Vector Machine regression, using a number of explicitly defined features extracted from the Machine Translation input, output and models in combination with tree kernels over constituency and dependency parse trees for the input and output sentences. We confirm earlier results suggesting that tree kernels can be a useful tool for QE system construction especially in the early stages of system design.

AB - This paper describes Uppsala University’s submissions to the Quality Estimation (QE) shared task at WMT 2012. We present a QE system based on Support Vector Machine regression, using a number of explicitly defined features extracted from the Machine Translation input, output and models in combination with tree kernels over constituency and dependency parse trees for the input and output sentences. We confirm earlier results suggesting that tree kernels can be a useful tool for QE system construction especially in the early stages of system design.

KW - Quality Estimation

KW - Machine Translation

KW - Support Vector Regression

KW - Tree Kernels

KW - Parse Trees

M3 - Article in proceedings

SN - 978-1-937284-20-6

SP - 109

EP - 113

BT - Proceedings of the Seventh Workshop on Statistical Machine Translation

ER -

Tree Kernels for Machine Translation Quality Estimation

Abstract

Keywords

Access to Document

Fingerprint

Cite this