Enriching Morphologically Poor Languages for Statistical Machine Translation

Eleftherios Avramidis; Philipp Koehn

Enriching Morphologically Poor Languages for Statistical Machine Translation

Eleftherios Avramidis, Philipp Koehn

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We address the problem of translating from morphologically poor to morphologically rich languages by adding per-word linguistic information to the source language. We use the syntax of the source sentence to extract information for noun cases and verb persons and annotate the corresponding words accordingly. In experiments, we show improved performance for translating from English into Greek and Czech. For English–Greek, we reduce the error on the verb conjugation from 19% to 5.4% and noun case agreement from 9% to 6%.

Original language	English
Title of host publication	Proceedings of ACL-08: HLT
Place of Publication	Columbus, Ohio
Publisher	Association for Computational Linguistics
Pages	763-770
Number of pages	8
Publication status	Published - 1 Jun 2008

Access to Document

P08 1087Final published version, 723 KB

http://www.aclweb.org/anthology/P/P08/P08-1087.pdf

Cite this

@inproceedings{ba40f7636cb5434cbb25936fdd46fff5,

title = "Enriching Morphologically Poor Languages for Statistical Machine Translation",

abstract = "We address the problem of translating from morphologically poor to morphologically rich languages by adding per-word linguistic information to the source language. We use the syntax of the source sentence to extract information for noun cases and verb persons and annotate the corresponding words accordingly. In experiments, we show improved performance for translating from English into Greek and Czech. For English–Greek, we reduce the error on the verb conjugation from 19% to 5.4% and noun case agreement from 9% to 6%.",

author = "Eleftherios Avramidis and Philipp Koehn",

year = "2008",

month = jun,

day = "1",

language = "English",

pages = "763--770",

booktitle = "Proceedings of ACL-08: HLT",

publisher = "Association for Computational Linguistics",

}

TY - GEN

T1 - Enriching Morphologically Poor Languages for Statistical Machine Translation

AU - Avramidis, Eleftherios

AU - Koehn, Philipp

PY - 2008/6/1

Y1 - 2008/6/1

N2 - We address the problem of translating from morphologically poor to morphologically rich languages by adding per-word linguistic information to the source language. We use the syntax of the source sentence to extract information for noun cases and verb persons and annotate the corresponding words accordingly. In experiments, we show improved performance for translating from English into Greek and Czech. For English–Greek, we reduce the error on the verb conjugation from 19% to 5.4% and noun case agreement from 9% to 6%.

AB - We address the problem of translating from morphologically poor to morphologically rich languages by adding per-word linguistic information to the source language. We use the syntax of the source sentence to extract information for noun cases and verb persons and annotate the corresponding words accordingly. In experiments, we show improved performance for translating from English into Greek and Czech. For English–Greek, we reduce the error on the verb conjugation from 19% to 5.4% and noun case agreement from 9% to 6%.

M3 - Conference contribution

SP - 763

EP - 770

BT - Proceedings of ACL-08: HLT

PB - Association for Computational Linguistics

CY - Columbus, Ohio

ER -

Enriching Morphologically Poor Languages for Statistical Machine Translation

Abstract

Access to Document

Fingerprint

Cite this