Exploiting morphology and local word reordering in English-to-Turkish Phrase-based statistical machine translation

I̊lknur Durgar El-Kahlout, Kemal Oflazer

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

In this paper, we present the results of our work on the development of a phrase-based statistical machine translation prototype from English to Turkishan agglutinative language with very productive inflectional and derivational morphology. We experiment with different morpheme-level representations for EnglishTurkish parallel texts. Additionally, to help with word alignment, we experiment with local word reordering on the English side, to bring the word order of specific English prepositional phrases and auxiliary verb complexes, in line with the morpheme order of the corresponding case-marked nouns and complex verbs, on the Turkish side. To alleviate the dearth of the parallel data available, we also augment the training data with sentences just with content word roots obtained from the original training data to bias root word alignment, and with highly reliable phrase-pairs from an earlier corpus alignment. We use a morpheme-based language model in decoding and a word-based language model in re-ranking the n-best lists generated by the decoder. Lastly, we present a scheme for repairing the decoder output by correcting words which have incorrect morphological structure or which are out-of-vocabulary with respect to the training data and language model, to further improve the translations. We improve from 15.53 BLEU points for our word-based baseline model to 25.17 BLEU points for an improvement of 9.64 points or about 62% relative.

Original languageEnglish
Article number5272404
Pages (from-to)1313-1322
Number of pages10
JournalIEEE Transactions on Audio, Speech and Language Processing
Volume18
Issue number6
DOIs
Publication statusPublished - 2010
Externally publishedYes

Fingerprint

machine translation
education
decoders
alignment
Decoding
Experiments
sentences
ranking
decoding
lists
maintenance
prototypes

Keywords

  • Complex morphology
  • English
  • statistical machine translation (SMT)
  • Turkish
  • word reordering

ASJC Scopus subject areas

  • Acoustics and Ultrasonics
  • Electrical and Electronic Engineering

Cite this

Exploiting morphology and local word reordering in English-to-Turkish Phrase-based statistical machine translation. / El-Kahlout, I̊lknur Durgar; Oflazer, Kemal.

In: IEEE Transactions on Audio, Speech and Language Processing, Vol. 18, No. 6, 5272404, 2010, p. 1313-1322.

Research output: Contribution to journalArticle

@article{a14d9977cd324580908fd0f77dbcc300,
title = "Exploiting morphology and local word reordering in English-to-Turkish Phrase-based statistical machine translation",
abstract = "In this paper, we present the results of our work on the development of a phrase-based statistical machine translation prototype from English to Turkishan agglutinative language with very productive inflectional and derivational morphology. We experiment with different morpheme-level representations for EnglishTurkish parallel texts. Additionally, to help with word alignment, we experiment with local word reordering on the English side, to bring the word order of specific English prepositional phrases and auxiliary verb complexes, in line with the morpheme order of the corresponding case-marked nouns and complex verbs, on the Turkish side. To alleviate the dearth of the parallel data available, we also augment the training data with sentences just with content word roots obtained from the original training data to bias root word alignment, and with highly reliable phrase-pairs from an earlier corpus alignment. We use a morpheme-based language model in decoding and a word-based language model in re-ranking the n-best lists generated by the decoder. Lastly, we present a scheme for repairing the decoder output by correcting words which have incorrect morphological structure or which are out-of-vocabulary with respect to the training data and language model, to further improve the translations. We improve from 15.53 BLEU points for our word-based baseline model to 25.17 BLEU points for an improvement of 9.64 points or about 62{\%} relative.",
keywords = "Complex morphology, English, statistical machine translation (SMT), Turkish, word reordering",
author = "El-Kahlout, {I̊lknur Durgar} and Kemal Oflazer",
year = "2010",
doi = "10.1109/TASL.2009.2033321",
language = "English",
volume = "18",
pages = "1313--1322",
journal = "IEEE Transactions on Audio, Speech and Language Processing",
issn = "1558-7916",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "6",

}

TY - JOUR

T1 - Exploiting morphology and local word reordering in English-to-Turkish Phrase-based statistical machine translation

AU - El-Kahlout, I̊lknur Durgar

AU - Oflazer, Kemal

PY - 2010

Y1 - 2010

N2 - In this paper, we present the results of our work on the development of a phrase-based statistical machine translation prototype from English to Turkishan agglutinative language with very productive inflectional and derivational morphology. We experiment with different morpheme-level representations for EnglishTurkish parallel texts. Additionally, to help with word alignment, we experiment with local word reordering on the English side, to bring the word order of specific English prepositional phrases and auxiliary verb complexes, in line with the morpheme order of the corresponding case-marked nouns and complex verbs, on the Turkish side. To alleviate the dearth of the parallel data available, we also augment the training data with sentences just with content word roots obtained from the original training data to bias root word alignment, and with highly reliable phrase-pairs from an earlier corpus alignment. We use a morpheme-based language model in decoding and a word-based language model in re-ranking the n-best lists generated by the decoder. Lastly, we present a scheme for repairing the decoder output by correcting words which have incorrect morphological structure or which are out-of-vocabulary with respect to the training data and language model, to further improve the translations. We improve from 15.53 BLEU points for our word-based baseline model to 25.17 BLEU points for an improvement of 9.64 points or about 62% relative.

AB - In this paper, we present the results of our work on the development of a phrase-based statistical machine translation prototype from English to Turkishan agglutinative language with very productive inflectional and derivational morphology. We experiment with different morpheme-level representations for EnglishTurkish parallel texts. Additionally, to help with word alignment, we experiment with local word reordering on the English side, to bring the word order of specific English prepositional phrases and auxiliary verb complexes, in line with the morpheme order of the corresponding case-marked nouns and complex verbs, on the Turkish side. To alleviate the dearth of the parallel data available, we also augment the training data with sentences just with content word roots obtained from the original training data to bias root word alignment, and with highly reliable phrase-pairs from an earlier corpus alignment. We use a morpheme-based language model in decoding and a word-based language model in re-ranking the n-best lists generated by the decoder. Lastly, we present a scheme for repairing the decoder output by correcting words which have incorrect morphological structure or which are out-of-vocabulary with respect to the training data and language model, to further improve the translations. We improve from 15.53 BLEU points for our word-based baseline model to 25.17 BLEU points for an improvement of 9.64 points or about 62% relative.

KW - Complex morphology

KW - English

KW - statistical machine translation (SMT)

KW - Turkish

KW - word reordering

UR - http://www.scopus.com/inward/record.url?scp=84988221520&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988221520&partnerID=8YFLogxK

U2 - 10.1109/TASL.2009.2033321

DO - 10.1109/TASL.2009.2033321

M3 - Article

VL - 18

SP - 1313

EP - 1322

JO - IEEE Transactions on Audio, Speech and Language Processing

JF - IEEE Transactions on Audio, Speech and Language Processing

SN - 1558-7916

IS - 6

M1 - 5272404

ER -