FLUX-CIM

• DOI: 10.1145/1255175.1255219
• Publication Date: 2007-09-14T16:07:37Z
• Authors: Eli Cortez; Altigran S. da Silva; Marcos André Gonç...; Filipe Mesquita; Edleno S. de Moura
• Keywords: Sample (material)

In this paper we propose a knowledge-base approach to help extracting the correct components of citations in any given format. Differently from related approaches that rely on manually built knowledge-bases (KBs) for recognizing citation, our case, such KB is automatically constructed an existing set sample metadata records area (e.g., computer science or health sciences). Our does not patterns encoding specific delimitators particular citation style. It also unsupervised, sense it learning method requires training phase. These features assign technique high degree automation and flexibility. To demonstrate effectiveness applicability proposed have run experiments which applied extract information papers two different domains. Results these indicate precision recall levels above 94% perfect extraction large majority tested.