CUED Publications database

Speed-constrained tuning for statistical machine translation using Bayesian optimization

Beck, D and De Gispert, A and Iglesias, G and Waite, A and Byrne, B (2016) Speed-constrained tuning for statistical machine translation using Bayesian optimization. In: UNSPECIFIED pp. 856-865..

Full text not available from this repository.

Abstract

©2016 Association for Computational Linguistics. We address the problem of automatically finding the parameters of a statistical machine translation system that maximize BLEU scores while ensuring that decoding speed exceeds a minimum value. We propose the use of Bayesian Optimization to efficiently tune the speed-related decoding parameters by easily incorporating speed as a noisy constraint function. The obtained parameter values are guaranteed to satisfy the speed constraint with an associated confidence margin. Across three language pairs and two speed constraint values, we report overall optimization time reduction compared to grid and random search. We also show that Bayesian Optimization can decouple speed and BLEU measurements, resulting in a further reduction of overall optimization time as speed is measured over a small subset of sentences.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:34
Last Modified: 03 Aug 2017 03:07
DOI: