cdec: A Decoder‚ Alignment‚ and Learning framework for finite−state and context−free translation models
Edinburgh Research Explorer (University of Edinburgh)Published 1 January 2010Open access
Chris Dyer, Adam Lopez, Juri Ganitkevitch, Jonathan Weese, Ferhan Türe, Phil Blunsom
Citations230
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.
Abstract
We present cdec, an open source frame-work for decoding, aligning with, and training a number of statistical machine translation models, including word-based models, phrase-based models, and models based on synchronous context-free gram-mars. Using a single unified internal representation for translation forests, the decoder strictly separates model-specific translation logic from general rescoring, pruning, and inference algorithms. From this unified representation, the decoder can extract not only the 1- or k-best transla-tions, but also alignments to a reference, or the quantities necessary to drive dis-criminative training using gradient-based or gradient-free optimization techniques. Its efficient C++ implementation means that memory use and runtime performance are significantly better than comparable decoders. 1
Keywords
Computer Science
Communications of the ACMMapReduce
18,538 Citations2008Jay B. Dean, Sanjay Ghemawat
This presentation explains how the underlying runtime system automatically parallelizes the computation across large-scale clusters of machines, handles machine failures, and schedules inter-machine communication to make efficient use of the network and disks.
Mathematical ProgrammingOn the limited memory BFGS method for large scale optimization
8,529 Citations1989Dong C. Liu, Jorge Nocedal
The numerical tests indicate that the L-BFGS method is faster than the method of Buckley and LeNir, and is better able to use additional storage to accelerate convergence, and the convergence properties are studied to prove global convergence on uniformly convex problems.
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.
The mathematics of statistical machine translation: parameter estimation
4,125 Citations1993Peter F. Brown, Vincent J. Della Pietra +2 more
It is reasonable to argue that word-by-word alignments are inherent in any sufficiently large bilingual corpus, given a set of pairs of sentences that are translations of one another.
IEEE International Conference on Neural NetworksA direct adaptive method for faster backpropagation learning: the RPROP algorithm
3,927 Citations2002Martin Riedmiller, Heinrich Braun
A learning algorithm for multilayer feedforward networks, RPROP (resilient propagation), is proposed that performs a local adaptation of the weight-updates according to the behavior of the error function to overcome the inherent disadvantages of pure gradient-descent.
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.
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.
A Study of Translation Edit Rate with Targeted Human Annotation
2,402 Citations2006Matthew Snover, Bonnie J. Dorr +3 more
A new, intuitive measure for evaluating machine translation output that avoids the knowledge intensiveness of more meaning-based approaches, and the labor-intensiveness of human judgments is defined.
Shallow parsing with conditional random fields
1,251 Citations2003Fei Sha, Fernando Pereira
This work shows how to train a conditional random field to achieve performance as good as any reported base noun-phrase chunking method on the CoNLL task, and better than any reported single model.
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.
Better<i>k</i>-best parsing
300 Citations2005Liang Huang, David Chiang
It is shown how the improved output of the efficient algorithms for k-best trees in the framework of hypergraph parsing has the potential to improve results from parse reranking systems and other applications.
Forest Rescoring: Faster Decoding with Integrated Language Models
290 Citations2007Liang Huang, David Chiang
This work develops faster approaches for efficient decoding based on k-best parsing algorithms and demonstrates their effectiveness on both phrase-based and syntax-based MT systems.
11,001 new features for statistical machine translation
238 Citations2009David Chiang, Kevin Knight +1 more
On a large-scale Chinese-English translation task, the Margin Infused Relaxed Algorithm is used to add a large number of new features to two machine translation systems: the Hiero hierarchical phrase-based translation system and the syntax-basedtranslation system.
Generalizing Word Lattice Translation
156 Citations2008Christopher J. Dyer, Smaranda Muresan +1 more
It is argued that word lattice decoding provides a compelling model for translation of text genres, as well, and that prior work in translating lattices using finite state techniques can be naturally extended to more expressive synchronous context-free grammarbased models.
First- and second-order expectation semirings with applications to minimum-risk training on translation forests
137 Citations2009Zhifei Li, Jason Eisner
A novel second-order expectation semiring is introduced, which computes second- order statistics and is essential for many interesting training paradigms such as minimum risk, deterministic annealing, active learning, and semi-supervised learning, where gradient descent optimization requires computing the gradient of entropy or risk.
Edinburgh Research Explorer (University of Edinburgh)A Discriminative Latent Variable Model for Statistical Machine Translation
115 Citations2008Phil Blunsom, Trevor Cohn +1 more
A translation model is presented which models derivations as a latent variable, in both training and decoding, and is fully discriminative and globally optimised, and results show that accounting for multiple derivations does indeed improve performance.
Edinburgh Research Explorer (University of Edinburgh)Hierarchical Phrase-Based Translation with Suffix Arrays
87 Citations2007Adam Lopez
This work describes new lookup algorithms for hierarchical phrase-based translation that reduce the empirical computation time by nearly two orders of magnitude, making on-the-fly lookup feasible for source phrases with gaps.
Efficient Minimum Error Rate Training and Minimum Bayes-Risk decoding for translation hypergraphs and lattices
81 Citations2009Shankar Kumar, Wolfgang Macherey +2 more
This work extends lattice-based MERT and MBR algorithms to work with hypergraphs that encode a vast number of translations produced by MT systems based on Synchronous Context Free Grammars, and shows how MERT can be employed to optimize parameters for MBR decoding.
Joshua: An open source toolkit for parsing-based machine translation
80 Citations2009Zhifei Li, Chris Callison-Burch +7 more
Computational LinguisticsWeighted Deductive Parsing and Knuth's Algorithm
72 Citations2003Mark-Jan Nederhof
Knuth's generalization of Dijkstra's algorithm for the shortest-path problem offers a general method to solve this problem and is modular in the sense that Knuth's algorithm is formulated independently from the weighted deduction system.
A syntax-directed translator with extended domain of locality
54 Citations2006Liang Huang, Kevin Knight +1 more
A syntax-directed translator first parses the source-language input into a parse-tree, and then recursively converts the tree into a string in the target-language, which gives the system more expressive power and flexibility.
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.
Context-free reordering, finite-state translation
37 Citations2010Chris Dyer, Philip Resnik
A class of translation model in which a set of input variants encoded as a context-free forest is translated using a finite-state translation model that has state-of-the-art translation performance, uses linguistically motivated features to effectively model long range reordering, and is significantly smaller than a comparable hierarchical phrase-based translation model.
Two monolingual parses are better than one (synchronous parse)
14 Citations2010Chris Dyer
It is demonstrated that for a number of common synchronous parsing problems, the two-parse algorithm substantially outperforms alternative synchronous parse strategies, making it efficient enough to be utilized without resorting to a pruned search.