Skip to Main content Skip to Navigation
Conference papers

Two Memory-Based Methods for Phrase Alignment

Johan Segura 1 Violaine Prince 1
1 TEXTE - Exploration et exploitation de données textuelles
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : This document presents two bilingual phrase-based alignment methods handling syntactic constituents (sub-sentential components) of parallel sentences. The methods relie on an asymmetrical parsing of both languages: Light part-of-speech tagging for the target language, syntactic tree building for the 'source' language and the complexity of each is studied. One of their benefits is that they do not require lexical knowledge for granting alignment. Another is that they align constituents of variable length and structure, thus providing information about divergent translations. Their originality rely on the fact that parsing of the supposed source language is reused both in resource building and alignment process. The models and methods can be seen as a subclass of Example Based Machine Translation.
Document type :
Conference papers
Complete list of metadata

Cited literature [20 references]  Display  Hide  Download
Contributor : Violaine Prince-Barbier <>
Submitted on : Monday, June 24, 2013 - 4:55:21 PM
Last modification on : Thursday, May 24, 2018 - 3:59:23 PM
Long-term archiving on: : Wednesday, September 25, 2013 - 4:11:34 AM


Files produced by the author(s)


  • HAL Id : lirmm-00838090, version 1



Johan Segura, Violaine Prince. Two Memory-Based Methods for Phrase Alignment. 5th Language and Technology Conference, Nov 2011, Poland. pp.101-110. ⟨lirmm-00838090⟩



Record views


Files downloads