Title :
A new approach of automatic Entity Relation Extraction combined multimachine learning
Author :
Suxiang, Zhang ; Suxian, Zhang
Author_Institution :
Dept. of Electron. & Commun. Eng., North China Electr. Power Univ., Baoding
Abstract :
Entity relation extraction is solved in this paper. Our approach is very different from previous approach; the conditional random fields (CRFs)-based machine learning is combined with the bootstrapping algorithm. Based on the bootstrapping algorithm, seed words and seed patterns were used to build a learning program, which extracts more characteristic words using scalar clusters as the important feature of CRFs algorithm. These characteristic words have semantic similarity with seed words. Moreover, Combined the CRFs algorithm, ten features have been proposed for entity relation extraction in this paper, which includes morphology, grammar and semantic feature. The system architecture used for entity relation extraction has been constructed. Experiment shows that the performance is promising. So it is useful to extract automatic entity relation.
Keywords :
computer bootstrapping; learning (artificial intelligence); automatic entity relation extraction; bootstrapping algorithm; conditional random field-based machine learning; multi-machine learning; scalar clusters; semantic feature; semantic similarity; Clustering algorithms; Data mining; Feature extraction; Kernel; Learning systems; Machine learning; Machine learning algorithms; Morphology; Natural languages; Power engineering and energy;
Conference_Titel :
Signal Processing, 2008. ICSP 2008. 9th International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-2178-7
Electronic_ISBN :
978-1-4244-2179-4
DOI :
10.1109/ICOSP.2008.4697434
