Tree as a Pivot: Syntactic Matching Methods in Pivot Translation

Pivot translation is a useful method for translating between languages with little or no parallel data by utilizing parallel data in an intermediate language such as English. A popular approach for pivot translation used in phrase-based or tree-based translation models combines source-pivot and pivot-target translation models into a source-target model, as known as triangulation . However, this combination is based on the constituent words’ surface forms and often produces incorrect source-target phrase pairs due to semantic ambiguity in the pivot language, and interlingual differences. This degrades translation accuracy. In this paper, we propose a approach for the triangulation using syntactic subtrees in the pivot language to distinguish pivot language words by their syntactic roles to avoid incorrect phrase combinations. Experimental results on the United Nations Parallel Corpus show the proposed method gains in all tested combinations of language, up to 2.3 BLEU points. 1

• Publication year

  2017

• Venue

  Conference on Machine Translation

• Publication date

  Unknown publication date

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.18653/v1/W17-4709
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation

  2016cited by this paper
• Zero-Resource Translation with Multi-Lingual Neural Machine Translation

  2016cited by this paper
• The United Nations Parallel Corpus v1.0

  2016influential reference
• Ckylark: A More Robust PCFG-LA Parser

  2015cited by this paper
• Improving Pivot Translation by Remembering the Pivot

  2015cited by this paper
• Travatar: A Forest-to-String Machine Translation Engine based on Tree Transducers

  2013cited by this paper
• Pointwise Prediction for Robust, Adaptable Japanese Morphological Analysis

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

  2011cited by this paper
• Fast, Easy, and Cheap: Construction of Statistical Machine Translation Models with MapReduce

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

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

  2007cited by this paper
• Hierarchical Phrase-Based Translation

  2007influential reference
• A Comparison of Pivot Methods for Phrase-Based Statistical Machine Translation

  2007cited by this paper
• Catalan-English Statistical Machine Translation without Parallel Corpus: Bridging through Spanish

  2006cited by this paper
• Training Tree Transducers

  2004cited by this paper
• Statistical Phrase-Based Translation

  2003influential reference
• Bleu: a Method for Automatic Evaluation of Machine Translation

  2002cited by this paper
• Computing the Edit-Distance between Unrooted Ordered Trees

  1998cited by this paper
• A Generalized CYK Algorithm for Parsing Stochastic CFG

  1998cited by this paper
• The Mathematics of Statistical Machine Translation: Parameter Estimation

  1993influential reference
• Syntax Directed Translations and the Pushdown Assembler

  1969cited by this paper

• Recent advances of low-resource neural machine translation

  2021cites this paper
• A neural interlingua for multilingual machine translation

  2018influential citation
• Pivot Machine Translation Using Chinese as Pivot Language

  2018cites this paper
• Syntactic Matching Methods in Pivot Translation

  2018cites this paper