Matches in ScholarlyData for { ?s ?p In order to relieve "News Information Overload", in this paper, we propose a novel approach of 5W1H (who, what, whom, when, where, how) event semantic elements extraction for Chinese news event knowledge base construction. The approach comprises a key event identification step, an event semantic elements extraction step and an event ontology population step. We first use a machine learning method to identify the key events of Chinese news stories. Then we employ SRL enhanced by rule-based method and NER technique to extract event 5W1H elements. At last we populate the extracted facts of news events to NOEM, an event ontology designed especially for modeling semantic elements and relations of events. We implement a prototype system based on proposed methods. Extensive experiments on real online news data sets confirm the reasonability and feasibility of our approach.. }
Showing items 1 to 1 of
1
with 100 items per page.
- 4 abstract "In order to relieve "News Information Overload", in this paper, we propose a novel approach of 5W1H (who, what, whom, when, where, how) event semantic elements extraction for Chinese news event knowledge base construction. The approach comprises a key event identification step, an event semantic elements extraction step and an event ontology population step. We first use a machine learning method to identify the key events of Chinese news stories. Then we employ SRL enhanced by rule-based method and NER technique to extract event 5W1H elements. At last we populate the extracted facts of news events to NOEM, an event ontology designed especially for modeling semantic elements and relations of events. We implement a prototype system based on proposed methods. Extensive experiments on real online news data sets confirm the reasonability and feasibility of our approach.".