Extracting Patterns of Semantic Roles from Accident Narratives

Abstract

Accident databases are filled with rich information about accidents. Analyzing these datasets can reveal useful information which can be used to prevent similar accidents in the future. Policy makers, and safety management organizations can design appropriate measures based on the analysis done to prevent accidents. Besides structured data, crash reports include natural language narratives which contain valuable accident-related information which is otherwise not present in the structured data. Using natural language processing (NLP) techniques one can analyze these narratives and mine hidden patterns of accidents from them. The thesis focuses on developing an algorithm to extract common patterns of semantic role labels from the narratives of accidents. These patterns capture frequently occurring sequences of verbs and their arguments. In this work, the developed algorithm was applied to accident narratives and the resulting patterns were assessed for their accident-related information.