High Performance Natural Language Processing on Semantic Network Array Processor

This paper describes a natural language processing system developed for the Semantic Network Array Processor (SNAP). The goal of our work is to develop a scalable and high-performance natural language processing system which utilizes the high degree of parallelism provided by the SNAP machine. We have implemented an experimental machine translation system as a central part of a real-time speech-to-speech dialogue translation system. It is a SNAP version of the DMDIAIOG speech-to-speech translation system. Memory-based natural language processing and syntactic constraint network model has been incorporated using parallel marker-passing which is directly supported from hardware level. Experimental results demonstrate that the parsing of a sentence is done in the order of milliseconds. 1 Introduction In this paper, we will demonstrate that natural language processing speeds in the order of milliseconds is attainable by using a marker-propagation algorithm and a specialized parallel hardware. The significance of the high-performance (or real-time) natural language processing is well known. Parsing sentences at the milliseconds speeds enables the realization of a speech recognition module capable of real-time speech understanding which eventually leads to the real-time simultaneous interpretation system. Also, the millisecond order performance enables the system to parse hundreds of sentences in a second , or over 3 million sentences per hour. This in turn makes possible bulk processing of text such as full-text retrieval, summarization, classification, translation, indexing and tagging. In order to accomplish the high-performance natural language processing, we have designed a highly parallel machine called Semantic Network Array Processor (SNAP) [Moldovan and Lee, 1990] [Lee and Moldovan, 19901, and implemented an experimental machine translation system called DMSN AP using a parallel marker-passing scheme. DM-SNAP is a SNAP implementation of the DMDIALOG speech-to-speech dialogue translation system [Kitano, 1990a) [Ki-tano, 1991a], but with some modifications to meet hardware constraints. Despite its high performance, our system carries out sound syntactic and se) antic analysis including lexical ambiguity, structural ambiguity, pronoun reference, control, unbounded dependency, and others. In the next section, we describe briefly the SNAP architecture , then, describe design philosophy behind the DMSNAP followed by descriptions on implementation and linguistic processing. Finally, performance are presented. 2 SNAP Architecture The Semantic Network Array Processor (SNAP) is a highly parallel array processor fully optimized for semantic network processing with marker-passing mechanism. In order to facilitate efficient propagation of markers and to case development of applications, a set of marker propagation instructions has been microcoded. SNAP supports …