Aligning Discourse and Argumentation Structures using Subtrees and Redescription Mining

Laurine Huber (1) , Yannick Toussaint (2) , Charlotte Roze (1) , Mathilde Dargnat (3) , Chloé Braud (1)

1 SYNALP - Natural Language Processing : representations, inference and semantics
2 ORPAILLEUR - Knowledge representation, reasonning
3 ATILF - Analyse et Traitement Informatique de la Langue Française

In this paper, we investigate similarities between discourse and argumentation structures by aligning subtrees in a corpus containing both annotations. Contrary to previous works, we focus on comparing sub-structures and not only relation matches. Using data mining techniques , we show that discourse and argumen-tation most often align well, and the double annotation allows to derive a mapping between structures. Moreover, this approach enables the study of similarities between discourse structures and differences in their expressive power.

Mots clés: argumentation structure; discourse structure; graph mining; data mining; redescription mining

Domaines: Traitement du texte et du document; Informatique et langage [cs.CL]; Algorithme et structure de données [cs.DS]; Recherche d'information [cs.IR]

Laurine Huber, Yannick Toussaint, Charlotte Roze, Mathilde Dargnat, Chloé Braud. Aligning Discourse and Argumentation Structures using Subtrees and Redescription Mining. 6th International Workshop on Argument Mining, Aug 2019, Florence, Italy. ⟨hal-02165048⟩