UNIGE document Doctoral Thesis
previous document  unige:75280  next document
add to browser collection

Algorithms and frameworks for Tree-based Machine Translation and tree structures prediction

Defense Thèse de doctorat : Univ. Genève, 2014 - Sc. 4809 - 2014/07/22
Abstract This thesis focuses on Hierarchical Machine Translation (HMT). HMT allows to model long distance phenomena and reordering at a cost of higher complexity of the decoder. With this thesis we reduce the complexity of HMT. In the first part we propose a series of alternative Cube Pruning (CP) algorithms that leverage on more aggressive pruning and less memory usage. Then we propose a linear time CP that solves exactly a relaxation of the decoding problem. All these algorithms can substitute the standard CP algorithm in any of its applications. In the second part of the thesis we present a novel Structured Prediction approach to HMT. The proposed model builds the structures incrementally, by choosing a single action at each step, and pruning all incompatible alternatives to that action. This approach allows translations to be constructed in an undirectional manner, thus not being constrained by the bottomup ordering of CKYlike algorithms.
URN: urn:nbn:ch:unige-752802
Full text
Thesis (2.4 MB) - public document Free access
Research groups Laboratoire d'Analyse et de Traitement du Langage (LATL)
Geneva Artificial Intelligence Laboratory
(ISO format)
GESMUNDO, Andréa. Algorithms and frameworks for Tree-based Machine Translation and tree structures prediction. Université de Genève. Thèse, 2014. https://archive-ouverte.unige.ch/unige:75280

252 hits



Deposited on : 2015-09-21

Export document
Format :
Citation style :