Abstract
This paper demonstrates the utility of the Semantic Network Array Processor (SNAP) as a massively parallel platform for high performance and large-scale natural language processing systems. SNAP is an experimental massively parallel machine which is dedicated to, but not limited to, the natural language processing using semantic networks. In designing the SNAP, we have investigated various natural language processing systems and theories to determine the scope of the hardware support and a set of micro-coded instructions to be provided. As a result, SNAP employs an extended marker-passing model and a dynamically modifiable network model. A set of primitive instructions is micro-coded to directly support a parallel marker-passing, bitoperations, numeric operations, network modifications, and other essential functions for natural language processing. This paper demonstrates the utility of SNAP for various paradigms of natural language processing. We have discovered that the SNAP provides milliseconds or microsectonds performance on several important applications such as the memory-based parsing and translation, classification-based parsing, and VLKB search. Also, we argue that there are numerous opportunities in the NLP community to take advantages of the computational power of the SNAP.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
