Wide Coverage Incremental Parsing by Learning Attachment Preferences

This paper presents a novel method for wide coverage parsing using an incremental strategy, which is psycholinguistically motivated. A recursive neural network is trained on treebank data to learn first pass attachments, and is employed as a heuristic for guiding parsing decision. The parser is lexically blind and uses beam search to explore the space of plausible partial parses and returns the full analysis having highest probability. Results are based on preliminary tests on the WSJ section of the Penn treebank and suggest that our incremental strategy is a computationally viable approach to parsing.