Using Bilingual Dependencies to Align Words in English/French Parallel Corpora

This paper describes a word and phrase alignment approach based on a dependency analysis of French/English parallel corpora, referred to as alignment by "syntax-based propagation." Both corpora are analysed with a deep and robust dependency parser. Starting with an anchor pair consisting of two words that are translations of one another within aligned sentences, the alignment link is propagated to syntactically connected words.

• Publication year

  2005

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  2005-06-27

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/1628960.1628984
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Identifying Correspondences Between Words: an Approach Based on a Bilingual Syntactic Analysis of French/English Parallel Corpora

  2004cited by this paper
• Simple linguistic methods for improving a word alignment algorithm

  2004cited by this paper
• ProAlign: Shared Task System Description

  2003cited by this paper
• An Evaluation Exercise for Word Alignment

  2003cited by this paper
• A Systematic Comparison of Various Statistical Alignment Models

  2003cited by this paper
• An algorithm for word-level alignment of parallel dependency trees

  2003cited by this paper
• Phrasal Cohesion and Statistical Machine Translation

  2002cited by this paper
• Evaluating Translational Correspondence using Annotation Projection

  2002cited by this paper
• A Syntax-based Statistical Translation Model

  2001cited by this paper
• Linguistic clues for corpus-based acquisition of lexical dependencies

  2001cited by this paper
• A knowledge-lite approach to word alignment

  2000cited by this paper
• Evaluation of parallel text alignment systems The ARCADE project

  2000cited by this paper
• Bracketing and aligning words and constituents in parallel text using Stochastic Inversion Transduction Grammars

  2000cited by this paper
• Evaluation of parallel text alignment systems

  2000cited by this paper
• Machine Translation Divergences: A Formal Description and Proposed Solution

  1994cited by this paper
• The Mathematics of Statistical Machine Translation: Parameter Estimation

  1993cited by this paper
• Identifying word correspondence in parallel texts

  1991cited by this paper
• Identifying Word Correspondences in Parallel Texts

  1991cited by this paper

• PartTUT: The Turin University Parallel Treebank

  2015cites this paper
• Exploiting catenae in a parallel treebank alignment

  2014cites this paper
• Dependency and Constituency in Translation Shift Analysis

  2013cites this paper
• The PERTOMed project

  2010cites this paper
• Exploiting linguistic and statistical knowledge in a text alignment system

  2009cites this paper