AcroDef: A Quality Measure for Discriminating Expansions of Ambiguous Acronyms

Mathieu Roche (1) , Violaine Prince (1)

1 TEXTE - Exploration et exploitation de données textuelles

This paper presents a set of quality measures to determine the choice of the best expansion for an acronym not defined in the Web page. The method uses statistics computed on Web pages to determine the appropriate expansion. Measures are context-based and rely on the assumption that the most frequent words in the page are related semantically or lexically to the acronym expansion.

Domaines: Autre; Intelligence artificielle [cs.AI]; Recherche d'information [cs.IR]; Web; Traitement du texte et du document

Mathieu Roche, Violaine Prince. AcroDef: A Quality Measure for Discriminating Expansions of Ambiguous Acronyms. CONTEXT, Aug 2007, Roskilde, Denmark. pp.411-424, ⟨10.1007/978-3-540-74255-5_31⟩. ⟨lirmm-00168945⟩