This research belongs to the Natural Language Processing (NLP) field and more specifically focuses on the topic of Sub-sentential Alignments which is closely related to Machine Translation. The originality of this work consists in an example-based approach bootstrapped by the participation of non-expert annotators through an appropriate interface. The quest for a greater expressivity, such as observed in manual alignments, mainly motivates the whole approach. An important effort has been made to define a formal environment for this original architecture based on aligned examples. Several memories have been created, using syntactic informations from parsers outputs with reasonnable low-tech requirements. Two new alignment methods were compar...
In this paper, we describe the architecture of a sub-sentential alignment system that links linguist...
iv L’amitie ́ se nourrit de communication. Michel de Montaigne vi The thesis work mainly focused on ...
International audienceThe approach suggested in this article enables statistic identification of low...
Cette thèse s'inscrit dans le cadre du traitement automatique du langage naturel, et traite plus pré...
Cette thèse s'inscrit dans le cadre du traitement automatique du langage naturel, et traite plus pré...
En linguistique informatique, la relation entre langues différentes est souventétudiée via des techn...
The goal of this thesis dissertation is to show that, contrary to preconceived ideas, one can effici...
La traduction statistique requiert des corpus parallèles en grande quantité. L’obtention de tels co...
Alignment consists of establishing a mapping between units in a bitext, combining a text in a source...
Le travail présenté dans cette thèse se place dans le contexte de l'alignement sous-phrastique. Une ...
In machine translation, the alignment of corpora has evolved into a mature research area, aimed at p...
Bitext alignment is the task of aligning a text in a source language and its translation in the targ...
International audienceThe focus of bilingual text alignment is automatic reconstruction of translati...
UnrestrictedAll state of the art statistical machine translation systems and many example-based mach...
The focus of this thesis is sub-sentential alignment, i.e. the automatic alignment of translational ...
In this paper, we describe the architecture of a sub-sentential alignment system that links linguist...
iv L’amitie ́ se nourrit de communication. Michel de Montaigne vi The thesis work mainly focused on ...
International audienceThe approach suggested in this article enables statistic identification of low...
Cette thèse s'inscrit dans le cadre du traitement automatique du langage naturel, et traite plus pré...
Cette thèse s'inscrit dans le cadre du traitement automatique du langage naturel, et traite plus pré...
En linguistique informatique, la relation entre langues différentes est souventétudiée via des techn...
The goal of this thesis dissertation is to show that, contrary to preconceived ideas, one can effici...
La traduction statistique requiert des corpus parallèles en grande quantité. L’obtention de tels co...
Alignment consists of establishing a mapping between units in a bitext, combining a text in a source...
Le travail présenté dans cette thèse se place dans le contexte de l'alignement sous-phrastique. Une ...
In machine translation, the alignment of corpora has evolved into a mature research area, aimed at p...
Bitext alignment is the task of aligning a text in a source language and its translation in the targ...
International audienceThe focus of bilingual text alignment is automatic reconstruction of translati...
UnrestrictedAll state of the art statistical machine translation systems and many example-based mach...
The focus of this thesis is sub-sentential alignment, i.e. the automatic alignment of translational ...
In this paper, we describe the architecture of a sub-sentential alignment system that links linguist...
iv L’amitie ́ se nourrit de communication. Michel de Montaigne vi The thesis work mainly focused on ...
International audienceThe approach suggested in this article enables statistic identification of low...