Exploring Difficulties in Parsing Imperatives and Questions

This paper analyzes the effect of the structural variation of sentences on parsing performance. We examine the performance of both shallow and deep parsers for two sentence constructions: imperatives and questions. We first prepare an annotated corpus for each of these sentence constructions by extracting sentences from a fiction domain that cover various types of imperatives and questions. The target parsers are then adapted to each of the obtained corpora as well as the existing query-focused corpus. Analysis of the experimental results reveals that the current mainstream parsing technologies and adaptation techniques cannot cope with different sentence constructions even with much in-domain data.