Otedama: Fast Rule-Based Pre-Ordering for Machine Translation

Abstract We present Otedama, a fast, open-source tool for rule-based syntactic pre-ordering, a well established technique in statistical machine translation. Otedama implements both a learner for pre-ordering rules, as well as a component for applying these rules to parsed sentences. Our system is compatible with several external parsers and capable of accommodating many source and all target languages in any machine translation paradigm which uses parallel training data. We demonstrate improvements on a patent translation task over a state-of-the-art English-Japanese hierarchical phrase-based machine translation system. We compare Otedama with an existing syntax-based pre-ordering system, showing comparable translation performance at a runtime speedup of a factor of 4.5-10.

• Publication year

  2016

• Venue

  Prague Bulletin of Mathematical Linguistics

• Publication date

  2016-10-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.1515/pralin-2016-0015
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Collaborative Development of a Rule-Based Machine Translator between Croatian and Serbian

  2016cited by this paper
• MARMOT: A Toolkit for Translation Quality Estimation at the Word Level

  2016cited by this paper
• Integrating Rules and Dictionaries from Shallow-Transfer Machine Translation into Phrase-Based Statistical Machine Translation

  2016cited by this paper
• Lexicographic Tools to Build New Encyclopaedia of the Czech Language

  2016cited by this paper
• Interoperability in MT Quality Estimation or wrapping useful stuff in various ways

  2016cited by this paper
• The ADAPT Bilingual Document Alignment system at WMT16

  2016cited by this paper
• Representing Documents and Queries as Sets of Word Embedded Vectors for Information Retrieval

  2016cited by this paper
• RuLearn: an Open-source Toolkit for the Automatic Inference of Shallow-transfer Rules for Machine Translation

  2016cited by this paper
• Qualitative: Python Tool for MT Quality Estimation Supporting Server Mode and Hybrid MT

  2016cited by this paper
• Efficient Word Alignment with Markov Chain Monte Carlo

  2016cited by this paper
• FaDA: Fast Document Aligner using Word Embedding

  2016cited by this paper
• Language Adaptation for Extending Post-Editing Estimates for Closely Related Languages

  2016cited by this paper
• DFKI’s system for WMT16 IT-domain task, including analysis of systematic errors

  2016cited by this paper
• A generalised alignment template formalism and its application to the inference of shallow-transfer machine translation rules from scarce bilingual corpora

  2015cited by this paper
• Improving Evaluation of Machine Translation Quality Estimation

  2015cited by this paper
• Fast and Accurate Preordering for SMT using Neural Networks

  2015cited by this paper
• Multi-level Translation Quality Prediction with QuEst++

  2015cited by this paper
• On an Apparent Freedom of Czech Word Order . A Case Study

  2015cited by this paper
• Large Scale Translation Quality Estimation

  2015cited by this paper
• DFKI’s experimental hybrid MT system for WMT 2015

  2015cited by this paper
• Management and Publishing of Multimedia Dictionary of the Czech Sign Language

  2015cited by this paper
• An open-source toolkit for word-level confidence estimation in machine translation

  2015cited by this paper
• Multi-Objective Optimization for the Joint Disambiguation of Nouns and Named Entities

  2015cited by this paper
• Reconstructions of Deletions in a Dependency-based Description of Czech: Selected Issues

  2015cited by this paper
• Efficient Top-Down BTG Parsing for Machine Translation Preordering

  2015cited by this paper
• Creation and Management of Structured Language Resources

  2015cited by this paper
• Bayesian Models for Multilingual Word Alignment

  2015cited by this paper
• Description of the Chinese-to-Spanish Rule-Based Machine Translation System Developed Using a Hybrid Combination of Human Annotation and Statistical Techniques

  2015cited by this paper
• Findings of the 2015 Workshop on Statistical Machine Translation

  2015cited by this paper
• Inferring Shallow-Transfer Machine Translation Rules from Small Parallel Corpora

  2014cited by this paper
• Correlating decoding events with errors in Statistical Machine Translation

  2014cited by this paper
• Statistical Machine Translation

  2014cited by this paper
• Qualitative: Open Source Python Tool for Quality Estimation over Multiple Machine Translation Outputs

  2014cited by this paper
• Source-side Preordering for Translation using Logistic Regression and Depth-first Branch-and-Bound Search

  2014cited by this paper
• Automatic Annotation of Machine Translation Datasets with Binary Quality Judgements

  2014cited by this paper
• The Role of Grammatical Constraints in Lexical Component in Functional Generative Description

  2014cited by this paper
• Genres in the Prague Discourse Treebank

  2014cited by this paper
• Verbs of Saying with a Textual Connecting Function in the Prague Discourse Treebank

  2014cited by this paper
• QuEst - A translation quality estimation framework

  2013cited by this paper
• Parsing with Compositional Vector Grammars

  2013cited by this paper
• Distributed Representations of Words and Phrases and their Compositionality

  2013cited by this paper
• MTMonkey: A Scalable Infrastructure for a Machine Translation Web Service

  2013cited by this paper
• Improving Statistical Machine Translation Using Bayesian Word Alignment and Gibbs Sampling

  2013cited by this paper
• Source-Side Classifier Preordering for Machine Translation

  2013cited by this paper
• A Systematic Bayesian Treatment of the IBM Alignment Models

  2013cited by this paper
• A Survey on Multi-view Learning

  2013cited by this paper
• Scalable Modified Kneser-Ney Language Model Estimation

  2013cited by this paper
• A Simple, Fast, and Effective Reparameterization of IBM Model 2

  2013cited by this paper
• How Dependency Trees and Tectogrammatics Help Annotating Coreference and Bridging Relations in Prague Dependency Treebank

  2013cited by this paper
• Exact Maximum Inference for the Fertility Hidden Markov Model

  2013cited by this paper
• Findings of the 2012 Workshop on Statistical Machine Translation

  2012cited by this paper
• Valence sloves v Pražském závislostním korpusu

  2012cited by this paper
• Alternative Lexicalizations of Discourse Connectives in Czech

  2012cited by this paper
• Quality estimation for Machine Translation output using linguistic analysis and decoding features

  2012cited by this paper
• Analyzing Parallelism and Domain Similarities in the MAREC Patent Corpus

  2012cited by this paper
• Comparative Quality Estimation: Automatic Sentence-Level Ranking of Multiple Machine Translation Outputs

  2012cited by this paper
• Aspects of discourse structure

  2012cited by this paper
• On scalarity in information structure

  2012cited by this paper
• Sentence Modality Assignment in the Prague Dependency Treebank

  2012cited by this paper
• An open-source toolkit for integrating shallow-transfer rules into phrase-based statistical machine translation

  2012cited by this paper
• Theoretical challenges in the transition from lexicographical p-works to e-tools

  2012cited by this paper
• Semi-Automatic Annotation of Intra-Sentential Discourse Relations in PDT

  2012cited by this paper
• Perspectives on crowdsourcing annotations for natural language processing

  2012cited by this paper
• Inducing a Discriminative Parser to Optimize Machine Translation Reordering

  2012influential reference
• Data access revisited: The Interactive Language Toolbox

  2012cited by this paper
• Machine Translation Infrastructure and Post-editing Performance at Autodesk

  2012cited by this paper
• Joint Feature Selection in Distributed Stochastic Learning for Large-Scale Discriminative Training in SMT

  2012cited by this paper
• Does Tectogrammatics Help the Annotation of Discourse?

  2012cited by this paper
• Improving the IBM Alignment Models Using Variational Bayes

  2012cited by this paper
• Random Search for Hyper-Parameter Optimization

  2012cited by this paper
• Bayesian Word Alignment for Statistical Machine Translation

  2011cited by this paper
• A Gold Standard for English-Swedish Word Alignment

  2011cited by this paper
• Scikit-learn: Machine Learning in Python

  2011cited by this paper
• Hjerson: An Open Source Tool for Automatic Error Classification of Machine Translation Output

  2011cited by this paper
• A Python Experiment Suite

  2011cited by this paper
• Unsupervised Word Alignment with Arbitrary Features

  2011cited by this paper
• Bitext Alignment

  2011cited by this paper
• Apertium: a free/open-source platform for rule-based machine translation

  2011cited by this paper
• KenLM: Faster and Smaller Language Model Queries

  2011cited by this paper
• Invented antonyms: Esperanto as a semantic lab

  2010cited by this paper
• Enriching Data-Oriented Parsing by blending morphology and syntax

  2010cited by this paper
• cdec: A Decoder, Alignment, and Learning Framework for Finite- State and Context-Free Translation Models

  2010cited by this paper
• Automatically Learning Source-side Reordering Rules for Large Scale Machine Translation

  2010influential reference
• Ways of Evaluation of the Annotators in Building the Prague Czech-English Dependency Treebank

  2010cited by this paper
• The Chain of Being and Having in Slavic

  2010cited by this paper
• Connective-Based Measuring of the Inter-Annotator Agreement in the Annotation of Discourse in PDT

  2010cited by this paper
• A Survey on Transfer Learning

  2010cited by this paper
• A Fast Fertility Hidden Markov Model for Word Alignment Using MCMC

  2010cited by this paper
• Rozšířená textová koreference a asociační anafora (koncepce anotace českých dat v pražském závislostním korpusu)

  2010cited by this paper
• Machine translation evaluation versus quality estimation

  2010cited by this paper
• A Note on the Implementation of Hierarchical Dirichlet Processes

  2009cited by this paper
• System for Querying Syntactically Annotated Corpora

  2009cited by this paper
• Transfer rule generation for a Japanese-Hungarian machine translation system

  2009cited by this paper
• Computational Experience with a Software Framework for Parallel Integer Programming

  2009cited by this paper
• A New Hybrid Dependency Parser for German

  2009influential reference
• Further Meta-Evaluation of Machine Translation

  2008cited by this paper
• The Penn Discourse TreeBank 2.0.

  2008cited by this paper
• Moses: Open Source Toolkit for Statistical Machine Translation

  2007cited by this paper
• (Meta-) Evaluation of Machine Translation

  2007cited by this paper
• Learning to rank: from pairwise approach to listwise approach

  2007cited by this paper

• Select and Reorder: A Novel Approach for Neural Sign Language Production

  2024cites this paper
• Improving Cross-Lingual Transfer through Subtree-Aware Word Reordering

  2023cites this paper
• Source side pre-ordering using recurrent neural networks for English-Myanmar machine translation

  2021cites this paper
• Exploiting Dependency-based Pre-ordering for English-Myanmar Statistical Machine Translation

  2019influential citation
• Exploiting Pre-Ordering for Neural Machine Translation

  2018influential citation