SAMPLING AND OPTIMIZATION IN PHRASE-BASED MACHINE TRANSLATION USING AN ENRICHED LANGUAGE MODEL REPRESENTATION

摘要

Rejection sampling is performed to acquire at least one target language translation for a source language string s in accordance with a phrase-based statistical translation model p(x)=p(t, a|s) where t is a candidate translation, a is a candidate alignment comprising a biphrase sequence generating the candidate translation t, and x is a sequence representing the candidate alignment a. The rejection sampling uses a proposal distribution comprising a weighted finite state automaton (WFSA) q(n) that is refined responsive to rejection of a sample x* obtained in a current iteration of the rejection sampling to generate a refined WFSA q(n+1) for use in a next iteration of the rejection sampling. The refined WFSA q(n+1) is selected to satisfy the criteria p(x)≦q(n+1)(x)≦q(n)(x) for all xεX and q(n+1)(x*)

主权项

1. A non-transitory storage medium storing instructions executable by an electronic data processing device to perform rejection sampling to acquire at least one accepted target language translation for a source language string s in accordance with a phrase-based statistical translation model
p(x)=p(t,a|s) where t is a candidate translation, a is a candidate alignment comprising a source language-target language biphrase sequence generating the candidate translation t, and x is a sequence representing the candidate alignment a, the rejection sampling using a proposal distribution comprising a weighted finite state automaton (WFSA) q(n) that is refined responsive to rejection of a sample x* obtained in a current iteration of the rejection sampling to generate a refined WFSA q(n+1) for use in a next iteration of the rejection sampling wherein the refined WFSA q(n+1) is selected to satisfy the criteria:
p(x)≦q(n+1)(x)≦q(n)(x) for all xεX; andq(n+1)(x*)