RI: Small: Developing Large Scale Distributed Syntactic, Semantic and Lexical Language Models for Machine Translation and Speech Recognition

RI：小型：开发用于机器翻译和语音识别的大规模分布式句法、语义和词汇语言模型

• 批准号: 1218863
• 负责人: Shaojun Wang
• 金额: $ 46万
• 依托单位: Wright State University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2012
• 资助国家: 美国
• 起止时间: 2012-08-01 至 2016-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1218863&HistoricalAwards=false
• 关键词: RI; Small; Developing; Large; Scale

This project aims to build large scale distributed syntactic, semantic, and lexical language models that are trained by corpora with up to Web-scale data on a supercomputer in order to substantially improve the performance of machine translation and speech recognition systems. It is conducted under the directed Markov random field paradigm to integrate both topics and syntax to form complex distributions for natural language, and uses hierarchical Pitman-Yor processes to model long-tail properties of natural language. By exploiting this particular structure, the complex statistical estimation and inference algorithms are decomposed and performed in a distributed environment. The language models are put into one-pass decoders of machine translation systems, and the lattice rescoring decoder into a speech recognition system. In addition, a principled solution to a long-standing open problem, smoothing fractional counts due to latent variables in Kneser-Ney's sense, might be found. This project fits into the NSF's strategic long term vision of a Cyber-infrastructure Framework for 21st Century Science and Engineering (CIF21). The project integrates various kinds of known language models and provides a way to overcome the limitations of existing combination methods for language models and to deploy algorithmically interesting methodologies that are scalable to data sets available on the Web. The project provides an environment for interdisciplinary education in information technology that bridges areas of language and speech processing, machine learning, and data-intensive science and engineering to benefit students at several levels.

该项目旨在构建大规模分布式句法、语义和词汇语言模型，并通过超级计算机上的语料库和网络规模的数据进行训练，以大幅提高机器翻译和语音识别系统的性能。 它在有向马尔可夫随机场范式下进行，整合主题和语法以形成自然语言的复杂分布，并使用分层 Pitman-Yor 过程对自然语言的长尾属性进行建模。 通过利用这种特殊的结构，复杂的统计估计和推理算法被分解并在分布式环境中执行。 将语言模型放入机器翻译系统的一次性解码器中，并将格重评分解码器放入语音识别系统中。 此外，可能会找到一个长期悬而未决的问题的原则性解决方案，即平滑由克内瑟-内伊意义上的潜在变量引起的分数计数。该项目符合 NSF 21 世纪科学与工程网络基础设施框架 (CIF21) 的战略长期愿景。 该项目集成了各种已知的语言模型，并提供了一种方法来克服现有语言模型组合方法的局限性，并部署可扩展至网络上可用数据集的算法上有趣的方法。 该项目为信息技术跨学科教育提供了一个环境，将语言和语音处理、机器学习以及数据密集型科学与工程领域联系起来，使多个层次的学生受益。