Modèles d’alignement probabilistes génératifs pour les mots et sous-mots : une exploration systématique des limites et potentialités des paramétrisations neuronales
Anh Khoa Ngo Ho · HAL (Le Centre pour la Communication Scientifique Directe) · 2021
Alignment consists of establishing a mapping between units in a bitext, combining a text in a source language and its translation in a target language. Alignments can be computed at several levels: between documents, between sentences, between phrases, between words, or even between smaller units end when one of the languages is morphologically complex, which implies to align fragments of words (morphemes). Alignments can also be considered between more complex linguistic structures such as trees or graphs. This is a complex, under-specified task that humans accomplish with difficulty. Its automation is a notoriously difficult problem in natural language processing, historically associated with the first probabilistic word-based translation models. The design of new models for natural language processing, based on distributed representations computed by neural networks, allows us to question and revisit the computation of these alignments. This research project, therefore, aims to comprehensively understand the limitations of existing statistical alignment models and to design neural models that can be learned without supervision to overcome these drawbacks and to improve the state of art in terms of alignment accuracy.