The Relationship Between Architectures and Example-Retrieval Times

Abstract

This paper proposes a method to find the most suitable architecture for a given response time requirement for Example-Retrieval (ER), which searches for the best match from a bulk collection of lingusitic examples. In the Example-Based Approach(EBA), which attains substantially higher accuracy than traditional approaches, ER is extensively used to carry out natural language processing tasks, e.g., parsing and translation. ER, however, is so computa-tionally demanding that it often takes up most of the total sentence processing time. This paper compares several accelerations of ER on differ-ent architectures, i.e., serial, MIMD and SIMD. Experimental results reveal the relationship be-tween architectures and response times, which will allows us to find the most suitable architec-ture for a given response time requirement.