|
Title:
|
PATTERN SIMILARITY BASED RELATION EXTRACTION FOR KNOWLEDGE GRAPH |
|
Author(s):
|
Yingju Xia, Zhongguang Zheng, Yao Meng and Jun Sun |
|
ISBN:
|
978-989-8533-82-1 |
|
Editors:
|
Pedro Isaías and Hans Weghorn |
|
Year:
|
2018 |
|
Edition:
|
Single |
|
Keywords:
|
Knowledge Graph, Semantic Web, Extraction Pattern, Pattern Similarity |
|
Type:
|
Poster / Demonstration |
|
First Page:
|
417 |
|
Last Page:
|
419 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Knowledge graphs represent information in the form of entities and relationships between them. A knowledge graph consists of multi-relational data, having entities as nodes and relations as edges. This paper presents a novel knowledge graph building method which using pattern similarity. The proposed method models the extraction pattern as a tag sequence and uses a Siamese network to learning the similarity between patterns. The pattern similarity can be used to extract new patterns for existing relations and find new relation patterns by clustering method. The experiments on large scale web pages show the effectiveness and efficiency of the proposed method. |
|
|
|
|
|
|
