Learning facts from semi-structured text

Details Learning facts from semi-structured text Learning facts from semi-structured text

G - Physics

06

F

G06F 17/30 (2006.01)

Patent

CA 2610208

A method and system of learning, or bootstrapping, facts from semi-structured text is described. Starting with a set of seed facts associated with an object, documents associated with the object are identified. The identified documents are checked to determine if each has at least a first predefined number of seed facts. If a document does have at least a first predefined number of seed facts, a contextual pattern associated with the seed facts is identified and other instances of content in the document matching the contextual pattern are identified. If the document includes at least a second predefined number of the other instances of content matching the contextual pattern, then facts may be extracted from the other instances.

L'invention se rapporte à un procédé et à un système d'apprentissage ou d'initialisation de faits à partir d'un texte semi-structuré. A partir d'un ensemble de faits de départ associés à un objet, on identifie des documents associés à l'objet. On vérifie les documents identifiés pour déterminer si chacun de ces documents possède au moins un premier nombre prédéfini de faits de départ. Si un document possède au moins un premier nombre prédéfini de faits de départ, on identifie un schéma contextuel associé aux faits de départ et on identifie d'autres exemples de contenu dans le document qui correspondent au schéma contextuel. Si le document contient au moins un deuxième nombre prédéfini des autres exemples de contenu qui correspondent au schéma contextuel, on peut ensuite extraire des faits à partir d'autres exemples.

Affiliated with

Also associated with

Rating

Learning facts from semi-structured text does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Learning facts from semi-structured text, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning facts from semi-structured text will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFCA-PAI-O-2001095