Decoding with Finite-State Transducers on GPUs

Weighted finite automata and transducers (including hidden Markov models and conditional random fields) are widely used in natural language processing (NLP) to perform tasks such as morphological analysis, part-of-speech tagging, chunking, named entity recognition, speech recognition, and others. Pa...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Argueta, Arturo, Chiang, David
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 17.01.2017
Subjects
Algorithms
Automata theory
Decoding
Graphics processing units
Markov chains
Natural language processing
Parallel processing
Speech recognition
Transducers
Online AccessGet full text

Cover

More Information
Summary:Weighted finite automata and transducers (including hidden Markov models and conditional random fields) are widely used in natural language processing (NLP) to perform tasks such as morphological analysis, part-of-speech tagging, chunking, named entity recognition, speech recognition, and others. Parallelizing finite state algorithms on graphics processing units (GPUs) would benefit many areas of NLP. Although researchers have implemented GPU versions of basic graph algorithms, limited previous work, to our knowledge, has been done on GPU algorithms for weighted finite automata. We introduce a GPU implementation of the Viterbi and forward-backward algorithm, achieving decoding speedups of up to 5.2x over our serial implementation running on different computer architectures and 6093x over OpenFST.
ISSN:2331-8422