Two Memory-Based Methods for Phrase Alignment - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Access content directly
Conference Papers Year : 2011

Two Memory-Based Methods for Phrase Alignment

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.
Fichier principal
Vignette du fichier
SNLP2011.pdf (119.88 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

lirmm-00838090 , version 1 (24-06-2013)

Identifiers

  • HAL Id : lirmm-00838090 , version 1

Cite

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

Share

Gmail Mastodon Facebook X LinkedIn More