A systematic analysis of translation model search spaces
Published 1 January 2009Open access
Michael Auli, Adam Lopez, Hieu Hoang, Philipp Koehn
Citations26
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
This work uses a simple technique to discover induction errors, which occur when good translations are absent from model search spaces, and suggests that the search spaces of phrase-based and hierarchical phrase- based models are highly overlapping despite the well known structural differences.
Abstract
Translation systems are complex, and most metrics do little to pinpoint causes of error or isolate system differences. We use a simple technique to discover induction errors, which occur when good translations are absent from model search spaces. Our results show that a common pruning heuristic drastically increases induction error, and also strongly suggest that the search spaces of phrase-based and hierarchical phrase-based models are highly overlapping despite the well known structural differences.
Keywords
Computer Science
Moses
4,868 Citations2007Philipp Koehn, Richard Zens +12 more
An open-source toolkit for statistical machine translation whose novel contributions are support for linguistically motivated factors, confusion network decoding, and efficient data formats for translation models and language models.
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.
Europarl: A Parallel Corpus for Statistical Machine Translation
3,106 Citations2005Philipp Koehn
A corpus of parallel text in 11 languages from the proceedings of the European Parliament is collected and its acquisition and application as training data for statistical machine translation (SMT) is focused on.
Minimum error rate training in statistical machine translation
2,766 Citations2003Franz Josef Och
It is shown that significantly better results can often be obtained if the final evaluation criterion is taken directly into account as part of the training procedure.
RWTH Publications (RWTH Aachen)Moses: Open Source Toolkit for Statistical Machine Translation
1,451 Citations2007Philipp Koehn, Hieu Hoang +12 more
Computational LinguisticsHierarchical Phrase-Based Translation
1,164 Citations2007David Chiang
A statistical machine translation model that uses hierarchical phrasesphrases that contain subphrasing that is formally a synchronous context-free grammar but is learned from a parallel text without any syntactic annotations is presented.
ACM Computing SurveysStatistical machine translation
406 Citations2008Adam Lopez
This survey presents a tutorial overview of the state of the art of statistical machine translation, describing the context of the current research and an overview of the main subproblems: translation modeling, parameter estimation, and decoding.
Edinburgh Research Explorer (University of Edinburgh)A fully Bayesian approach to unsupervised part-of-speech tagging
280 Citations2007Sharon Goldwater, Thomas L. Griffiths
This model has the structure of a standard trigram HMM, yet its accuracy is closer to that of a state-of-the-art discriminative model (Smith and Eisner, 2005), up to 14 percentage points better than MLE.
A systematic comparison of phrase-based, hierarchical and syntax-augmented statistical MT
93 Citations2008Andreas Zollmann, Ashish Venugopal +2 more
This work investigates the source of the improvements in translation quality reported when using two PSCFG translation models (hierarchical and syntax-augmented), when extending a state-of-the-art phrase-based baseline that serves as the lexical support for both P SCFG models.
Going beyond AER
85 Citations2006Necip Fazıl Ayan, Bonnie J. Dorr
It is shown that precision-oriented alignments yield better MT output (translating more words and using longer phrases) than recall-orientedalignments, and new measures for intrinsic evaluations are introduced.
Empirical lower bounds on the complexity of translational equivalence
65 Citations2006Benjamin Wellington, Sonjia Waxmonsky +1 more
The study found that the complexity of these patterns in every bitext was higher than suggested in the literature, and shed new light on why "syntactic" constraints have not helped to improve statistical translation models, including finite-state phrase-based models, tree-to-string models, and tree- to-tree models.
Artificial IntelligenceFast and optimal decoding for machine translation
52 Citations2003Ulrich Germann, Michael Jahr +3 more
This paper compares the speed and output quality of a traditional stack-based decoding algorithm with two new decoders: a fast but non-optimal greedy decoder and a slow but optimal decoder that treats decoding as an integer-programming optimization problem.
Tera-scale translation models via pattern matching
50 Citations2008Adam Lopez
It is shown how an algorithmic scaling technique can be used to easily handle very large models and show an improvement 1.4 BLEU on the NIST 2006 Chinese-English task.
Extracting synchronous grammar rules from word-level alignments in linear time
43 Citations2008Hao Zhang, Daniel Gildea +1 more
The algorithm generalize Uno and Yagiura's algorithm for finding all common intervals of two permutations to the setting of two sequences with many-to-many alignment links across the two sides is generalized and used to maximally decompose a word-aligned sentence pair in linear time.
Probabilistic inference for machine translation
43 Citations2008Phil Blunsom, Miles Osborne
The power of the discriminative training paradigm is demonstrated by extracting structured syntactic features, and achieving increases in translation performance, by approximating the intractable space of all candidate translations produced by intersecting an ngram language model with a synchronous grammar.
Comparing reordering constraints for SMT using efficient Bleu oracle computation
29 Citations2007Markus Dreyer, Keith Hall +1 more
An empirical evaluation of popular reordering constraints: local constraints, the IBM constraints, and the Inversion Transduction Grammar (ITG) constraints are presented and it is shown that reordering under the ITG constraints can improve over the baseline by more than 7.5 Bleu points.
Multi-source translation methods
18 Citations2008Lane Schwartz
It is shown that the MAX multilingual multi-source hypothesis ranking method presented by Och and Ney (2001) does not reliably improve translation quality when a broad range of language pairs are considered and an oracle experiment shows that current hypothesis ranking methods fall far short of the best results reachable via sentence-level ranking.