Graph-Based Knowledge Consolidation in Ontology Population

スポンサーリンク

概要

• 論文の詳細を見る

• We propose a novel method for knowledge consolidation based on a knowledge graph as a next step in relation extraction from text. The knowledge consolidation method consists of entity consolidation and relation consolidation. During the entity consolidation process, identical entities are found and merged using both name similarity and relation similarity measures. In the relation consolidation process, incorrect relations are removed using cardinality properties, temporal information and relation weight in given graph structure. In our experiment, we could generate compact and clean knowledge graphs where number of entities and relations are reduced by 6.1% and by 17.4% respectively with increasing relation accuracy from 77.0% to 85.5%.

著者

• Park So-young

  Division Of Digital Media Technology Sangmyung University

• Kim Hyun-ki

  Speech/language Information Research Center Etri

• Jang Myung-gil

  Speech/language Information Research Center Etri

• RYU Pum

  Speech/Language Information Research Center, ETRI

関連論文

• Automatic Acronym Dictionary Construction Based on Acronym Generation Types
• Estimating Translation Probabilities Considering Semantic Recoverabilitv of Phrase Retranslation
• Detecting Partial and Near Duplication in the Blogosphere
• Descriptive Question Answering with Answer Type Independent Features
• Graph-Based Knowledge Consolidation in Ontology Population

スポンサーリンク