Decoding with Finite-State Transducers on GPUs

01/11/2017
by   Arturo Argueta, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/16/2018

Composing Finite State Transducers on GPUs

Weighted finite-state transducers (FSTs) are frequently used in language...
research
03/09/2017

Turkish PoS Tagging by Reducing Sparsity with Morpheme Tags in Small Datasets

Sparsity is one of the major problems in natural language processing. Th...
research
04/09/2018

A GPU-based WFST Decoder with Exact Lattice Generation

We describe initial work on an extension of the Kaldi toolkit that suppo...
research
06/14/2022

An Experimental Investigation of Part-Of-Speech Taggers for Vietnamese

Part-of-speech (POS) tagging plays an important role in Natural Language...
research
02/17/2021

Introducing the Hidden Neural Markov Chain framework

Nowadays, neural network models achieve state-of-the-art results in many...
research
02/17/2021

Highly Fast Text Segmentation With Pairwise Markov Chains

Natural Language Processing (NLP) models' current trend consists of usin...
research
10/06/2021

CTC Variations Through New WFST Topologies

This paper presents novel Weighted Finite-State Transducer (WFST) topolo...

Please sign up or login with your details

Forgot password? Click here to reset