Speaker: Mohammed Alliheedi, PhD Candidate
Over the past decade, the focus on argumentation mining has been growing significantly in different areas of Artificial Intelligence (AI) research. The incentive to build Natural Language Processing (NLP) systems to automatically identify and analyze argumentative components in various genres of texts has increased because knowledge of argumentative structure facilitates various tasks such as text summarization and opinion mining for commercial purposes. In particular, researchers are developing automated argumentation analysis systems to enable scientists in the experimental sciences to review and evaluate scientific findings more efficiently, and to help identify whether scientific claims are valid or not, based on their argumentative structure. However, these approaches have lacked consistency in their definitions of argumentation "schemes" (i.e., labels used to identify the different components of an argumentative structure). Moreover, there has been no formal, computationally feasible, semantics for these schemes. In this research we will work on the biochemistry domain to develop a formal knowledge representation, procedurally rhetorical frame semantics, that can be used for in-depth argumentation analysis, is computationally feasible to implement, and will enable argumentation mining of more-detailed scientific knowledge than is currently available.