Collecting Semantic Data by Mechanical Turk for the Lexical Knowledge Resource of a Text-to-Picture Generating System

WordsEye is a system for automatically converting natural language text into 3D scenes representing the meaning of that text. 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. To enrich a portion of the SBLR, we need to fill out some contextual information about its objects, including information about their typical parts, typical locations and typical objects located near them. This paper explores our proposed methodology to achieve this goal. First we try to collect some semantic information by using Amazon’s Mechanical Turk (AMT). Then, we manually filter and classify the collected data and finally, we compare the manual results with the output of some automatic filtration techniques which use several WordNet similarity and corpus association measures.