Data collection and normalization for building the Scenario-Based Lexical Knowledge Resource of a text-to-scene conversion system

WordsEye is a system for converting from English text into three-dimensional graphical scenes that represent that text. It works by performing syntactic and semantic analyses on the input text, producing a description of the arrangement of objects in a scene. At the core of WordsEye is the Scenario-Based Lexical Knowledge Resource (SBLR), a unified knowledge base and representational system for expressing lexical and real-world knowledge needed to depict scenes from text. This paper explores information collection methods for building the SBLR, using Amazon's Mechanical Turk (AMT) and manual normalization of raw AMT data. The paper follows with manual review of existing relations in the SBLR and classification of the AMT data into existing and new semantic relations. Since manual annotation is a time-consuming and expensive approach, we also explored the use of automatic normalization of AMT data through log-odds and log-likelihood ratios extracted from the English Gigaword corpus, as well as through WordNet similarity measures.