Research and Development of SNAP: Semantic Network Array Processor

SNAP：语义网络阵列处理器的研发

• 批准号: 9009109
• 负责人: Dan Moldovan
• 金额: $ 116.5万
• 依托单位: University of Southern California
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 1990
• 资助国家: 美国
• 起止时间: 1990-09-01 至 1993-11-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9009109&HistoricalAwards=false
• 关键词: Research; Development; SNAP; Semantic; Network

This is part of a joint project at Carnegie Mellon University and the University of Southern California to build a massively parallel processor and use it for natural language translation. The system to be built is an array of custom processors that are specialized for marker passing in semantic networks. A specific goal of this project is to implement a real-time speech-to-speech dialogue translation system with about 500 words in its vocabulary. This system will necessarily include natural language understanding and generation components. The culmination of this project will be an array of 16,384 semantic network nodes with software implementing the translation system.

这是卡内基梅隆大学联合项目的一部分， 南加州大学建立一个大规模的平行 处理器并将其用于自然语言翻译。 要构建的系统是一系列定制处理器， 专门用于语义网络中的标记传递。 特定 本项目的目标是实现一个实时语音到语音 对话翻译系统，其词汇量约为500个单词。 这个系统必然包括自然语言理解 和发电组件。 该项目的最终成果将 是一个由16,384个语义网络节点组成的数组， 翻译系统的实现。