Challenges of argument mining: generating an argument synthesis based on the Qualia structure

Patrick Saint Dizier (1)

1 IRIT-ADRIA - Argumentation, Décision, Raisonnement, Incertitude et Apprentissage

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.

Mots clés: Generative Lexicon

Domaines: Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]; Logique en informatique [cs.LO]; Informatique et langage [cs.CL]

Patrick Saint Dizier. Challenges of argument mining: generating an argument synthesis based on the Qualia structure. 9th International Conference on Natural Language Generation (INLG 2016), Sep 2016, Edinburgh, United Kingdom. pp. 79-83. ⟨hal-01436199⟩