arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1701.03038cs.CLcs.DC
收藏

在GPU上使用双态转换器进行解码

Decoding with Finite-State Transducers on GPUs

University of Notre Dame(圣母大学)

Arturo Argueta, David Chiang

摘要:

加权有限自动机和转换器(包括隐马尔可夫模型和条件随机场)广泛用于自然语言处理(NLP)中以执行诸如形态分析、词性标注、组块、命名实体识别、语音识别等任务。在图形处理单元(GPU)上实现有限状态算法将有利于NLP的许多领域。虽然研究人员已经实现了GPU版本的基本图形算法,有限的以前的工作,据我们所知,已经做了加权有限自动机的GPU算法。我们介绍了一个GPU实现的维特比和前向-后向算法,实现了高达5.2倍的解码加速比我们的串行实现运行在不同的计算机体系结构和6093倍的OpenFST。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑