Pharaoh: A Beam Search Decoder for Phrase-Based Statistical Machine Translation Models
Lecture notes in computer sciencePublished 1 January 2004
Philipp Koehn
Citations634
SJR quartileQ2
SJR score0.35
SNIP0.55
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
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.
Abstract
We describe Pharaoh, a freely available decoder for phrase-based statistical machine translation models. The decoder is the implement at ion of an efficient dynamic programming search algorithm with lattice generation and XML markup for external components.
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.
Journal of the American Statistical AssociationStatistical Methods for Speech Recognition
1,988 Citations1999Don X. Sun, Frederick Jelinek
The speech recognition problem hidden Markov models the acoustic model basic language modelling the Viterbi search hypothesis search on a tree and the fast match elements of information theory.
RPK (Politechniki Krakowskiej)Artificial Intelligence: A Modern Approach
1,746 Citations1995Stuart Russell, Peter Norvig
Discriminative training and maximum entropy models for statistical machine translation
1,044 Citations2001Franz Josef Och, Hermann Ney
A framework for statistical machine translation of natural languages based on direct maximum entropy models, which contains the widely used source-channel approach as a special case and shows that a baseline statistical machinetranslation system is significantly improved using this approach.
Wiley Encyclopedia of Electrical and Electronics EngineeringComputational Linguistics
834 Citations1999Fred Popowich
A phrase-based, joint probability model for statistical machine translation
475 Citations2002Daniel Marcu, William Wong
A joint probability model for statistical machine translation is presented, which automatically learns word and phrase equivalents from bilingual corpora, which is more accurate than translations produced using IBM Model 4.
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.
Finding the k shortest paths
330 Citations2002David Eppstein
K shortest paths are given for finding the k shortest paths connecting a pair of vertices in a digraph, and applications to dynamic programming problems including the knapsack problem, sequence alignment, and maximum inscribed polygons are described.
Munich Personal RePEc Archive (Ludwig Maximilian University of Munich)Minimum Bayes-risk decoding for statistical machine translation
330 Citations2004Shankar Kumar, Bill Byrne
The results show that MBR decoding can be used to tune statistical MT performance for specific loss functions, and a hierarchy of loss functions that incorporate different levels of linguistic information from word strings, word-to-word alignments from an MT system, and syntactic structure from parse-trees of source and target language sentences.
Decoding complexity in word-replacement translation models
259 Citations1999Kevin Knight
Computational LinguisticsWord Reordering and a Dynamic Programming Beam Search Algorithm for Statistical Machine Translation
257 Citations2003Christoph Tillmann, Hermann Ney
A novel technique to restrict the possible word reorderings between source and target language in order to achieve an efficient search algorithm for statistical machine translation based on dynamic programming (DP).
RWTH Publications (RWTH Aachen)Statistical machine translation : from single-word models to alignment templates
149 Citations2002Franz Josef Och
Generation of word graphs in statistical machine translation
113 Citations2002Nicola Ueffing, Franz Josef Och +1 more
A method for constructing a word graph to represent alternative hypotheses in an efficient way to ensure that these hypotheses can be rescored using a refined language or translation model.
Feature-rich statistical translation of noun phrases
106 Citations2003Philipp Koehn, Kevin Knight
A dedicated noun phrase translation subsystem is built that improves over the currently best general statistical machine translation methods by incorporating special modeling and special features.
The CMU Statistical Machine Translation System
89 Citations2003Stephan Vogel, Ying Zhang +5 more
This paper describes the components of a statistical machine translation system that combines phrase-to-phrase translations extracted from a bilingual corpus using different alignment approaches and shows how a manual lexicon can be incorporated into the statistical system in an optimized way.
Greedy decoding for statistical machine translation in almost linear time
73 Citations2003Ulrich Germann
Improvements to a greedy decoding algorithm for statistical machine translation are presented that reduce its time complexity from at least cubic (O(n6) when applied naively) to practically linear time1 without sacrificing translation quality.
A projection extension algorithm for statistical machine translation
68 Citations2003Christoph Tillmann
A phrase- based unigram model for statistical machine translation that uses a much simpler set of model parameters than similar phrase-based models that has been successfully test on a Chinese-English and an Arabic-English translation task.
Word re-ordering and DP-based search in statistical machine translation
54 Citations2000Christoph Tillmann, Hermann Ney
A novel technique to restrict the possible word reordering between source and target language in order to achieve an efficient search algorithm for statistical machine translation based on dynamic programming.
Noun phrase translation
50 Citations2003Kevin Knight, Philipp Koehn
A dedicated noun phrase translation subsystem is built that improves over the currently best general statistical machine translation methods by incorporating special modeling and special features and shows overall improvement in translation quality.