Challenges of Argument Mining: Generating an Argument Synthesis based on the Qualia Structure

摘要

Given a controversial issue, argument mining from texts in natural language is extremely challenging: besides linguistic aspects, domain knowledge is often required together with appropriate forms of inferences to identify arguments. A major challenge is then to organize the arguments which have been mined to generate a synthesis that is relevant and usable. We show that the Generative Lexicon (GL) Qualia structure, enhanced in different manners and associated with inferences and language patterns, allows to capture the typical concepts found in arguments and to organize a relevant synthesis.