Syntactic reordering for English-Arabic phrase-based machine translation
Published 1 January 2009Open access
Jakob Elming, Nizar Habash
Citations34
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A pre-translation syntactic reordering approach developed on a close language pair (English-Danish) to the distant language pair, English-Arabic, proves the viability of this approach for distant languages.
Abstract
We investigate syntactic reordering within an English to Arabic translation task.We extend a pre-translation syntactic reordering approach developed on a close language pair (English-Danish) to the distant language pair, English-Arabic.We achieve significant improvements in translation quality over related approaches, measured by manual as well as automatic evaluations.These results prove the viability of this approach for distant languages.
Keywords
Computer Science
Computational LinguisticsA Systematic Comparison of Various Statistical Alignment Models
3,928 Citations2003Franz Josef Och, Hermann Ney
An important result is that refined alignment models with a first-order dependence and a fertility model yield significantly better results than simple heuristic models.
Statistical phrase-based translation
3,268 Citations2003Philipp Koehn, Franz Josef Och +1 more
The empirical results suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning of phrase translations from word-based alignments and lexical weighting of phrase translation.
A maximum-entropy-inspired parser
1,496 Citations2000Eugene Charniak
A new parser for parsing down to Penn tree-bank style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less and 89.5% when trained and tested on the previously established sections of the Wall Street Journal treebank is presented.
A hierarchical phrase-based model for statistical machine translation
1,161 Citations2005David Chiang
The model is formally a synchronous context-free grammar but is learned from a bitext without any syntactic information, which can be seen as a shift to the formal machinery of syntax-based translation systems without any linguistic commitment.
A syntax-based statistical translation model
736 Citations2001Kenji Yamada, Kevin Knight
This model transforms a source-language parse tree into a target-language string by applying stochastic operations at each node, and produces word alignments that are better than those produced by IBM Model 5.
Lecture notes in computer sciencePharaoh: A Beam Search Decoder for Phrase-Based Statistical Machine Translation Models
634 Citations2004Philipp Koehn
Pharaoh, a freely available decoder for phrase-based statistical machine translation models is described, which is the implement at ion of an efficient dynamic programming search algorithm with lattice generation and XML markup for external components.
Clause restructuring for statistical machine translation
619 Citations2005Michael Collins, Philipp Koehn +1 more
The reordering approach is applied as a pre-processing step in both the training and decoding phases of a phrase-based statistical MT system, showing an improvement from 25.2% Bleu score for a baseline system to 26.8% Blee score for the system with reordering.
What's in a Translation Rule
465 Citations2004Michel Galley, Mark Hopkins +2 more
The theory is used to introduce a linear algorithm that can be used to derive from word-aligned, parallel corpora the minimal set of syntactically motivated transformation rules that explain human translation data.
(Meta-) evaluation of machine translation
385 Citations2007Chris Callison-Burch, Cameron Shaw Fordyce +3 more
An extensive human evaluation was carried out not only to rank the different MT systems, but also to perform higher-level analysis of the evaluation process, revealing surprising facts about the most commonly used methodologies.
Edinburgh Research Explorer (University of Edinburgh)Edinburgh System Description for the 2005 IWSLT Speech Translation Evaluation
366 Citations2005Philipp Koehn, Amittai Axelrod +4 more
This work adapted the statistical machine translation system that performed successfully in previous DARPA competitions on open domain text translations to work on limited domain speech data in the IWSLT 2005 speech translation task.
Lecture notes in computer sciencePhrase-Based Statistical Machine Translation
365 Citations2002Richard Zens, Franz Josef Och +1 more
A translation model that is based on bilingual phrases to explicitly model the local context is presented and it is shown that this model performs better than the single-word based model.
Text, speech and language technologyOn Arabic Transliteration
309 Citations2007Nizar Habash, Abdelhadi Soudi +1 more
This chapter introduces the transliteration scheme used to represent Arabic characters in this book and presents guidelines for Arabic pronunciation using this transliterations scheme.
Manual and automatic evaluation of machine translation between European languages
276 Citations2006Philipp Koehn, Christof Monz
This work evaluated machine translation performance for six European language pairs that participated in a shared task: translating French, German, Spanish texts to English and back.
Improving a statistical MT system with automatically learned rewrite patterns
271 Citations2004Fei Xia, Michael C. McCord
This work proposes to use automatically learned rewrite patterns to preprocess the source sentences so that they have a word order similar to that of the target language.
Arabic preprocessing schemes for statistical machine translation
254 Citations2006Nizar Habash, Fatiha Sadat
Learning trees and rules with set-valued features
244 Citations1996William W. Cohen
It is argued that many decision tree and rule learning algorithms can be easily extended to set-valued features, and it is shown by example that many real-world learning problems can be efficiently and naturally represented with set- valued features.
Chinese Syntactic Reordering for Statistical Machine Translation
216 Citations2007Chao Wang, Michael J. Collins +1 more
A set of syntactic reordering rules that exploit systematic differences between Chinese and English word order are described, which are used as a preprocessor for both training and test sentences, transforming Chinese sentences to be much closer to English in terms of their word order.
Text, speech and language technologyArabic Computational Morphology: Knowledge-based and Empirical Methods
198 Citations2007Abdelhadi Soudi, Günter Neumann +1 more
Morphological analysis for statistical machine translation
177 Citations2004Young‐Suk Lee
A novel morphological analysis technique which induces a morphological and syntactic symmetry between two languages with highly asymmetrical morphological structures to improve statistical machine translation qualities.
Interpreting BLEU/NIST Scores: How Much Improvement Do We Need to Have a Better System?
165 Citations2004Ying Zhang, Stephan Vogel +1 more
A novel method of calculating the confidence intervals for BLEU/NIST scores using bootstrapping is reported, which can determine whether two MT systems are significantly different from each other.
A maximum entropy word aligner for Arabic-English machine translation
115 Citations2005Abraham Ittycheriah, Salim Roukos
It is demonstrated that it is feasible to create training material for problems in machine translation and that a mixture of supervised and unsupervised methods yields superior performance.
A Probabilistic Approach to Syntax-based Reordering for Statistical Machine Translation
87 Citations2007Chi-Ho Li, Minghui Li +4 more
A novel, probabilistic approach to reordering which combines the merits of syntax and phrase-based SMT is proposed, which leads to BLEU improvement of 1.56% for the NIST MT-05 task of Chinese-toEnglish translation.
Syntactic preprocessing for statistical machine translation.
85 Citations2007Nizar Habash
Segmentation for English-to-Arabic statistical machine translation
68 Citations2008Ibrahim Badr, Rabih Zbib +1 more
It is shown that morphological decomposition of the Arabic source is beneficial, especially for smaller-size corpora, and recombination techniques are investigated, and the use of Factored Translation Models for English-to-Arabic translation is reported on.
Edinburgh Research Explorer (University of Edinburgh)Word-Based Alignment, Phrase-Based Translation: What's the Link?
55 Citations2006Adam Lopez, Philip Resnik
This work investigates the impact of high-quality alignments with a carefully constructed set of degraded alignments, and confirms a weak correlation, but illustrates that more data and better feature engineering may be more beneficial than better alignment.
IWSLTImproved chunk-level reordering for statistical machine translation.
33 Citations2007Yuqi Zhang, Richard Zens +1 more
Two methods to improve the reordering at the chunk level by introducing a new lattice weighting factor and by reordering the training source data are presented, reporting an improvement on TER and BLEU.
Joint morphological-lexical language modeling for machine translation
26 Citations2007Ruhi Sarikaya, Yonggang Deng
The proposed JMLLM takes advantage of the rich morphology to reduce the Out-Of-Vocabulary rate, while keeping the predictive power of the whole words, and allows incorporation of additional available semantic, syntactic and linguistic information about the morphemes and words into the language model.
Syntax-enhanced n-gram-based SMT.
24 Citations2007Josep Crego, José Bernardo Mariño Acebal
Columbia Academic Commons (Columbia University)Challenges in Building an Arabic-English GHMT System with SMT Components
15 Citations2006Nizar Habash, Bonnie J. Dorr +1 more
The challenges in building an Arabic-English generation-heavy machine translation system and boosting it with statistical machine translation (SMT) components are described and positive results on the advantages of hybridization are reported.