A Discriminative Training Procedure for Continuous Translation Models

Do, Quoc-Khanh; Allauzen, Alexandre; Yvon, François

doi:10.18653/v1/d15-1121

Cited by 2 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall, we were able to report results that surpass a conventional phrase-based system by more than 2.5 BLEU points. This work thus extends (Do et al, 2015b) by providing a thorough comparison of a much wider array of training criteria expressed here in a generic framework.…”

Section: Introductionmentioning

confidence: 79%

A comparison of discriminative training criteria for continuous space translation models

Allauzen

Khanh

Yvon

2017

Machine Translation

Self Cite

View full text Add to dashboard Cite

This paper explores a new discriminative training procedure for continuousspace translation models (CTMs) which correlates better with translation quality than conventional training methods. The core of the method lays in the definition of a novel objective function which enables us to effectively integrate the CTM with the rest of the translation system through N-best rescoring. Using a fixed architecture, where we iteratively retrain the CTM parameters and the log-linear coefficients, we compare various ways to define and combine training criteria for each of these steps, drawing inspirations both from max-margin and learning-to-rank techniques. We experimentally show that a recently introduced loss function, which combines these two techniques, outperforms several objective functions from the literature. We also show that ensuring the consistency of the losses used to train these two sets of parameters is beneficial to the overall performance.

show abstract

Section: Introductionmentioning

confidence: 79%