Automated Extraction of Function Knowledge From Text

Abstract

This paper presents a method to automatically extract function knowledge from natural language text. The extraction method uses syntactic rules to acquire subject-verb-object (SVO) triplets from parsed text. Then, the functional basis taxonomy, WordNet, and word2vec are utilized to classify the triplets as artifact-function-energy flow knowledge. For evaluation, the function definitions associated with 30 most frequent artifacts compiled in a human-constructed knowledge base, Oregon State University's design repository (DR), were compared to the definitions identified by extraction the method from 4953 Wikipedia pages classified under the category “Machines.” The method found function definitions for 66% of the test artifacts. For those artifacts found, 50% of the function definitions identified were compiled in the DR. In addition, 75% of the most frequent function definitions found by the method were also defined in the DR. The results demonstrate the potential of the current work in enabling automated construction of function knowledge repositories.