2014 | OriginalPaper | Buchkapitel
Extraction of Relation Descriptors for Portuguese Using Conditional Random Fields
verfasst von : Sandra Collovini, Lucas Pugens, Aline A. Vanin, Renata Vieira
Erschienen in: Advances in Artificial Intelligence -- IBERAMIA 2014
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
An important task in Information Extraction is Relation Extraction. Relation Extraction (RE) is the task of detecting and characterizing the semantic relations between entities in the text. This work proposes a new process for the extraction of any relation descriptors between Named Entities (NEs) in the Organization domain, for the Portuguese language, using the Conditional Random Fields (CRF) model. For example, from the following sentence fragment
“Microsoft headquartered in Redmond, […]”,
we can extract the relation descriptor “
headquartered-in
”, that relates the NEs
“Microsoft”
and
“Redmond”
. We evaluated different features configurations for CRF; the best results were obtained with the inclusion of the
semantic feature
based on the NE category, since this feature could express, in a better way, the kind of relationship between the pair of NEs we want to identify. The proposed process achieved F-measure rates of 45 % and 53 %, considering the extraction of complete and partial matching, respectively.