Document-Wide Decoding for Phrase-Based Statistical Machine Translation
Edinburgh Research ExplorerPublished 12 July 2012Open access
Christian Hardmeier, Joakim Nivre, Jörg Tiedemann
Citations74
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 proposes a stochastic local search decoding method for phrase-based SMT, which permits free document-wide dependencies in the models and explores the stability and the search parameters of this method and demonstrates that it can be successfully used to optimise a document-level semantic language model.
Abstract
Independence between sentences is an assumption deeply entrenched in the models and algorithms used for statistical machine translation (SMT), particularly in the popular dynamic programming beam search decoding algorithm. This restriction is an obstacle to research on more sophisticated discourse-level models for SMT. We propose a stochastic local search decoding method for phrase-based SMT, which permits free document-wide dependencies in the models. We explore the stability and the search parameters of this method and demonstrate that it can be successfully used to optimise a document-level semantic language model. 1
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.
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.
Automatic evaluation of machine translation quality using n-gram co-occurrence statistics
1,605 Citations2002George R. Doddington
NIST commissioned NIST to develop an MT evaluation facility based on the IBM work, which is now available from NIST and serves as the primary evaluation measure for TIDES MT research.
KenLM: Faster and Smaller Language Model Queries
1,142 Citations2011Kenneth Heafield
KenLM is a library that implements two data structures for efficient language model queries, reducing both time and memory costs and is integrated into the Moses, cdec, and Joshua translation systems.
Discourse and the Translator
1,113 Citations2014Basil Hatim, Ian Mason
Issues and debate in translation studies linguistics and translators - theory and practice context in translating and languages as discourse translating text as signs the semiotic dimension of context intertextuality and intentionality in semiotic translating text type as the translator's focus prose designs - text structure discourse texture the translator as mediator.
Proceedings of the IEEEExploiting latent semantic information in statistical language modeling
352 Citations2000J.R. Bellegarda
This paper focuses on the use of latent semantic analysis, a paradigm that automatically uncovers the salient semantic relationships between words and documents in a given corpus, and proposes an integrative formulation for harnessing this synergy.
IRSTLM: an open source toolkit for handling large scale language models
324 Citations2008Marcello Federico, Nicola Bertoldi +1 more
The IRSTLM toolkit supports distribution of ngram collection and smoothing over a computer cluster, language model compression through probability quantization, lazy-loading of huge language models from disk.
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).
Fast decoding and optimal decoding for machine translation
234 Citations2001Ulrich 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 greedy decoder and a slow but optimal decoder that treats decoding as an integer-programming optimization problem.
Empirical Methods in Natural Language ProcessingImproving Translation Quality by Discarding Most of the Phrasetable
201 Citations2007Howard Johnson, Joel Martin +2 more
It is possible to reduce the bulk of phrasetables for Statistical Machine Translation using a technique based on the significance testing of phrase pair co-occurrence in the parallel corpus and an improvement in BLEU is obtained at the same time although the effect is less pronounced if state-of-the-art phrasetic smoothing is employed.
Edinburgh Research Explorer (University of Edinburgh)Modelling Pronominal Anaphora in Statistical Machine Translation
115 Citations2010Christian Hardmeier, Marcello Federico
A word dependency model is presented for SMT, which can represent links between word pairs in the same or in different sentences, and is used to integrate the output of a coreference resolution system into English-German SMT with a view to improving the translation of anaphoric pronouns.
The S-Space Package: An Open Source Package for Word Space Models
101 Citations2010David Jurgens, Keith Stevens
The S-Space Package implements well-known word space algorithms, such as LSA, and provides a comprehensive set of matrix utilities and data structures for extending new or existing models and includes word space benchmarks for evaluation.
Edinburgh Research Explorer (University of Edinburgh)Aiding Pronoun Translation with Co-Reference Resolution
101 Citations2010Ronan Le Nagard, Philipp Koehn
A method to improve the translation of pronouns by resolving their co- reference to prior mentions by using two different co-reference resolution methods is proposed.
Cache-based Document-level Statistical Machine Translation
97 Citations2011Zhengxian Gong, Min Zhang +1 more
This paper presents three kinds of caches to store relevant document-level information: a dynamic cache, which stores bilingual phrase pairs from the best translation hypotheses of previous sentences in the test document; a static cache,which stores relevantilingual phrase pairs extracted from similar bilingual document pairs in the training parallel corpus; and a topic cache,Which stores the target-side topic words related with the test documents in the source-side.
An efficient A* search algorithm for statistical machine translation
95 Citations2001Franz Josef Och, Nicola Ueffing +1 more
This paper describes an efficient A* search algorithm for statistical machine translation and develops various so-phisticated admissible and almost admissible heuristic functions that allow to translate even long sentences.
A DP based search using monotone alignments in statistical translation
84 Citations1997C. Tillmann, Stephan Vogel +2 more
A Dynamic Programming (DP) based search algorithm for statistical translation uses a first-order Hidden Markov model as they are used successfully in speech recognition for the time alignment problem.
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.
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.
ArXiv.orgMethods to integrate a language model with semantic information for a word prediction component
38 Citations2008Tonio Wandmacher, Jean-Yves Antoine
This work explores the predictive powers of Latent Semantic Analysis (LSA), a method that has been shown to provide reliable information on long-distance semantic dependencies between words in a context, and presents and evaluates several methods that integrate LSA-based information with a standard language model: a semantic cache, partial reranking, and different forms of interpolation.
Machine TranslationBilingual LSA-based adaptation for statistical machine translation
37 Citations2007Yik-Cheung Tam, Ian Lane +1 more
A novel approach to cross-lingual language model and translation lexicon adaptation for statistical machine translation (SMT) based on bilingual latent semantic analysis with rapid bootstrapping of LSA models for new languages based on a source LSA model of another language.
Meeting of the Association for Computational LinguisticsA Semantic Feature for Statistical Machine Translation
34 Citations2011Rafael E. Banchs, Marta R. Costa‐jussà
A semantic feature for statistical machine translation, based on Latent Semantic Indexing, is proposed and evaluated, which aims at favoring those translation units that were extracted from training sentences that are semantically related to the current input sentence being translated.
Cross-lingual latent semantic analysis for language modeling
27 Citations2004Woosung Kim, Sanjeev Khudanpur
This work uses ideas from cross-lingual latent semantic analysis to develop a single low-dimensional representation shared by words and documents in both languages, which enables it to find documents in the resource-rich language pertaining to a specific story in a resource-deficient language.
Monte carlo inference and maximization for phrase-based translation
25 Citations2009Abhishek Arun, Chris Dyer +4 more
A novel Gibbs sampler is defined for sampling translations given a source sentence and it is shown that it effectively explores this posterior distribution of sampling defined by a translation model.
Local Search with Very Large-Scale Neighborhoods for Optimal Permutations in Machine Translation
22 Citations2006Jason Eisner, Roy W. Tromble
A novel decoding procedure for statistical machine translation and other ordering tasks based on a family of Very Large-Scale Neighborhoods, some of which have previously been applied to other NP-hard permutation problems are introduced.
To Cache or Not To Cache? Experiments with Adaptive Models in Statistical Machine Translation
17 Citations2010Jörg Tiedemann
A system that includes adaptive language and translation models that is implemented using exponentially decaying caches storing previous translations as the history for new predictions is applied to the WMT 2010 shared translation task.
Machine TranslationMonte Carlo techniques for phrase-based translation
13 Citations2010Abhishek Arun, Barry Haddow +4 more
A novel Gibbs sampler is defined for sampling translations given a source sentence and it is shown that it effectively explores this posterior distribution of sampling defined by a translation model.