First Steps towards Multi-Engine Machine Translation

We motivate our contribution to the shared MT task as a first step towards an integrated architecture that combines advantages of statistical and knowledge-based approaches. Translations were generated using the Pharaoh decoder with tables derived from the provided alignments for all four languages, and for three of them using web-based and locally installed commercial systems. We then applied statistical and heuristic algorithms to select the most promising translation out of each set of candidates obtained from a source sentence. Results and possible refinements are discussed.

• Publication year

  2005

• Venue

  ParallelText@ACL

• Publication date

  2005-06-29

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/1654449.1654483
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Multi-engine machine translation guided by explicit word matching

  2005cited by this paper
• The Proper Place of Men and Machines in Language Translation

  2004cited by this paper
• Multi-Engine Machine Translation with Voted Language Model

  2004cited by this paper
• Interpreting BLEU/NIST Scores: How Much Improvement do We Need to Have a Better System?

  2004cited by this paper
• Pharaoh: A Beam Search Decoder for Phrase-Based Statistical Machine Translation Models

  2004cited by this paper
• SRILM - an extensible language modeling toolkit

  2002cited by this paper
• Using Language and Translation Models to Select the Best among Outputs from Multiple MT Systems

  2002cited by this paper
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002cited by this paper
• Robust Translation of Spontaneous Speech: A Multi-Engine Approach

  2001cited by this paper
• A program for automatically selecting the best output from multiple machine translation engines

  2001cited by this paper
• Computing consensus translation from multiple machine translation systems

  2001cited by this paper
• Statistical multi-source translation

  2001cited by this paper
• Using multiple edit distances to automatically rank machine translation output

  2001cited by this paper
• Learning to Select a Good Translation

  2000cited by this paper
• An evaluation of the multi-engine MT architecture

  1998cited by this paper
• Hybrid language processing in the Spoken Language Translator

  1997cited by this paper
• Three Heads are Better than One

  1994cited by this paper

• Hybrid Machine Translation by Combining Output from Multiple Machine Translation Systems

  2019cites this paper
• Combined Use of Rule-Based and Corpus-Based Methods in Machine Translation

  2012cites this paper
• Deep Syntax in Statistical Machine Translation

  2011cites this paper
• Choosing the best machine translation system to translate a sentence by using only source-language information

  2011cites this paper
• EUSMT: incorporating linguistic information to SMT for a morphologically rich language. Its use in SMT-RBMT-EBMT hybridation

  2010cites this paper
• Hierarchical Hybrid Translation between English and German

  2010cites this paper
• Integrating a Rule-based with a Hierarchical Translation System

  2010cites this paper
• Word Lattices for Multi-Source Translation

  2009cites this paper
• Building a Multilingual Lexical Resource for Named Entity Disambiguation, Translation and Transliteration

  2008cites this paper
• Choosing the Right Translation: A Syntactically Informed Classification Approach

  2008cites this paper
• Hybrid machine translation architectures within and beyond the EuroMatrix project

  2008cites this paper
• Hybrid Architectures for Multi-Engine Machine Translation

  2008cites this paper
• Projecting Temporal Annotations Across Languages

  2007cites this paper
• Multi-Engine Machine Translation with an Open-Source SMT Decoder

  2007cites this paper
• Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora

  2007cites this paper
• D 6 . 1 : Improved confidence estimation and hybrid architectures for machine translation

  2007cites this paper
• Multi-Engine Machine Translation with an Open-Source SMT Decoder

  2007cites this paper