Massively Parallel Suffix Array Queries and On-Demand Phrase Extraction for Statistical Machine Translation Using GPUs
Dept. of Computer Science, University of Maryland, College Park, Maryland
The 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL HLT), 2013
@article{he2013massively,
title={Massively Parallel Suffix Array Queries and On-Demand Phrase Extraction for Statistical Machine Translation Using GPUs},
author={He, Hua and Lin, Jimmy and Lopez, Adam},
year={2013}
}
Translation models can be scaled to large corpora and arbitrarily-long phrases by looking up translations of source phrases on the fly in an indexed parallel text. However, this is impractical because on-demand extraction of phrase tables is a major computational bottleneck. We solve this problem by developing novel algorithms for general purpose graphics processing units (GPUs), which enable suffix array queries for phrase lookup and phrase extractions to be massively parallelized. Our open-source implementation improves the speed of a highly-optimized, state-of-the-art serial CPU-based implementation by at least an order of magnitude. In a Chinese-English translation task, our GPU implementation extracts translation tables from approximately 100 million words of parallel text in less than 30 milliseconds.
April 18, 2013 by hgpu
