Research on semantic label extraction of domain entity relation based on CRF and rules
APWeb'12 Proceedings of the 14th international conference on Web Technologies and Applications
| Hi-index | 0.00 |
To solve the difficulty of the field of Automatic Entity Relation Extraction, in this paper, a method that used binary classification thinking, meanwhile combined with reasoning rules to extract the field of entity relation is proposed. considering comprehensively the context information of entity, entity type and their combination of characteristics to construct the feature set, which in order to build the Binary Classifier of entity relation extraction, then taking full advantage of the field characteristics of entity relation, further combine reasoning rules to obtain the type of the field of entity relation. Doing our experiment on the artificial collection of 600 corpuses for tourism field, experimental result shows the method of Binary Classifier combining Reasoning is better than Multiple Classifiers, the F-score is improved 3%.