Augmenting String-to-Tree and Tree-to-String Translation with Non-Syntactic Phrases

Matthias Huck; Hieu Hoang; Philipp Koehn

Augmenting String-to-Tree and Tree-to-String Translation with Non-Syntactic Phrases

Matthias Huck, Hieu Hoang, Philipp Koehn

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

Abstract

We present an effective technique to easily augment GHKM-style syntax-based machine translation systems (Galley et al., 2006) with phrase pairs that do not comply with any syntactic well-formedness constraints. Non-syntactic phrase pairs are distinguished from syntactic ones in order to avoid harming effects. We apply our technique in state-of-the-art string-to-tree and tree-to-string setups. For tree-to-string translation, we furthermore investigate novel approaches for translating with source-syntax GHKM rules in association with input tree constraints and input tree features.

Original language	English
Title of host publication	Proceedings of the Ninth Workshop on Statistical Machine Translation
Place of Publication	Baltimore, Maryland, USA
Publisher	Association for Computational Linguistics
Pages	486-498
Number of pages	13
Publication status	Published - 1 Jun 2014

Access to Document

W14-3362Final published version, 170 KB

http://www.aclweb.org/anthology/W14-3362

MosesCore Co-ord - 'Moses Open Source Evaluation and Support Co-ordination for OutReach and Exploitation'
Koehn, P. (Principal Investigator)
EU government bodies
1/02/12 → 31/01/15
Project: Research
EU-Bridge
Renals, S. (Principal Investigator), King, S. (Co-investigator), Koehn, P. (Co-investigator) & Osborne, M. (Co-investigator)
EU government bodies
1/02/12 → 31/01/15
Project: Research

Cite this

@inproceedings{b463f6fd6c4a40e28f752ab91c46f2bc,

title = "Augmenting String-to-Tree and Tree-to-String Translation with Non-Syntactic Phrases",

abstract = "We present an effective technique to easily augment GHKM-style syntax-based machine translation systems (Galley et al., 2006) with phrase pairs that do not comply with any syntactic well-formedness constraints. Non-syntactic phrase pairs are distinguished from syntactic ones in order to avoid harming effects. We apply our technique in state-of-the-art string-to-tree and tree-to-string setups. For tree-to-string translation, we furthermore investigate novel approaches for translating with source-syntax GHKM rules in association with input tree constraints and input tree features.",

author = "Matthias Huck and Hieu Hoang and Philipp Koehn",

year = "2014",

month = jun,

day = "1",

language = "English",

pages = "486--498",

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

publisher = "Association for Computational Linguistics",

}

Augmenting String-to-Tree and Tree-to-String Translation with Non-Syntactic Phrases. / Huck, Matthias; Hoang, Hieu; Koehn, Philipp.
Proceedings of the Ninth Workshop on Statistical Machine Translation. Baltimore, Maryland, USA: Association for Computational Linguistics, 2014. p. 486-498.

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

TY - GEN

T1 - Augmenting String-to-Tree and Tree-to-String Translation with Non-Syntactic Phrases

AU - Huck, Matthias

AU - Hoang, Hieu

AU - Koehn, Philipp

PY - 2014/6/1

Y1 - 2014/6/1

N2 - We present an effective technique to easily augment GHKM-style syntax-based machine translation systems (Galley et al., 2006) with phrase pairs that do not comply with any syntactic well-formedness constraints. Non-syntactic phrase pairs are distinguished from syntactic ones in order to avoid harming effects. We apply our technique in state-of-the-art string-to-tree and tree-to-string setups. For tree-to-string translation, we furthermore investigate novel approaches for translating with source-syntax GHKM rules in association with input tree constraints and input tree features.

AB - We present an effective technique to easily augment GHKM-style syntax-based machine translation systems (Galley et al., 2006) with phrase pairs that do not comply with any syntactic well-formedness constraints. Non-syntactic phrase pairs are distinguished from syntactic ones in order to avoid harming effects. We apply our technique in state-of-the-art string-to-tree and tree-to-string setups. For tree-to-string translation, we furthermore investigate novel approaches for translating with source-syntax GHKM rules in association with input tree constraints and input tree features.

M3 - Conference contribution

SP - 486

EP - 498

BT - Proceedings of the Ninth Workshop on Statistical Machine Translation

PB - Association for Computational Linguistics

CY - Baltimore, Maryland, USA

ER -

Augmenting String-to-Tree and Tree-to-String Translation with Non-Syntactic Phrases

Abstract

Access to Document

Fingerprint

Projects

MosesCore Co-ord - 'Moses Open Source Evaluation and Support Co-ordination for OutReach and Exploitation'

EU-Bridge

Cite this