Incremental Parsing in Bounded Memory

This tutorial will describe the use of a factored probabilistic sequence model for parsing speech and text using a bounded store of three to four incomplete constituents over time, in line with recent estimates of human shortterm working memory capacity. This formulation uses a grammar transform to minimize memory usage during parsing. Incremental operations on incomplete constituents in this transformed representation then define an extended domain of locality similar to those defined in mildly context-sensitive grammar formalisms, which can similarly be used to process long-distance and crossed-and-nested dependencies.