Boeing’s NLP System and the Challenges of Semantic Representation

We describe Boeing's NLP system, BLUE, comprising a pipeline of a parser, a logical form (LF) generator, an initial logic generator, and further processing modules. The initial logic generator produces logic whose structure closely mirrors the structure of the original text. The subsequent processing modules then perform, with somewhat limited scope, additional transformations to convert this into a more usable representation with respect to a specific target ontology, better able to support inference. Generating a semantic representation is challenging, due to the wide variety of semantic phenomena which can occur in text. We identify seventeen such phenomena which occurred in the STEP 2008 "shared task" texts, comment on BLUE's ability to handle them or otherwise, and discuss the more general question of what exactly constitutes a "semantic representation", arguing that a spectrum of interpretations exist.