Truly Parallel Understanding of Text

Abstract

Understanding a text requires two basic tasks: making inferences at several levels of knowledge and composing a global interpretation of the given text from those various types of inferences. Since making inferences at each level demands an extensive computations, there have been several attempts to use parallel inference mechanisms such as parallel marker passing (PMP) to increase the productivity of the inference mecha nism. Such a mechanism, when used with many local processors, is capable of making inferences in parallel. However, it often poses a large burden on the task of composing the global interpretation by producing a number of meaningless inferences which should be filtered out. Therefore, the increased productivity of the inference mechanism causes the slow down of the task of forming the global interpretation and makes it the bottleneck of the whole system. Our system, TRUE, effectively solves this problem with the Constrained Marker Passing mechanism. The new mechanism not only allows the system to make necessary inferences in parallel, but also provides a way to compose the global interpretation in parallel. Therefore, the system is truly parallel, and does not suffer from any single bottleneck.