Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Joint Entity and Relation Extraction for Free Text


Affiliations
1 Department of CSE, Dr. M.G.R Educational and Research Institute University, Chennai, India
     

   Subscribe/Renew Journal


Both entity and relation extraction can benefit from being performed jointly, allowing each task to correct the errors of the other. The syntactic knowledge extraction is specific knowledge extraction, which automatically extracts the characteristic words and patterns based on hierarchy bootstrapping machine learning. A new method for joint entity and relation extraction using a graph called as a “card-pyramid”. This graph compactly encodes all possible entities and relations in a sentence, reducing the task of their joint extraction to jointly labeling its nodes. An efficient labeling algorithm that is analogous to parsing using dynamic programming. The experiment demonstrates the benefit of joint entity and relation extraction.
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 261

PDF Views: 3




  • Joint Entity and Relation Extraction for Free Text

Abstract Views: 261  |  PDF Views: 3

Authors

R. Karthika
Department of CSE, Dr. M.G.R Educational and Research Institute University, Chennai, India
S. Geetha
Department of CSE, Dr. M.G.R Educational and Research Institute University, Chennai, India

Abstract


Both entity and relation extraction can benefit from being performed jointly, allowing each task to correct the errors of the other. The syntactic knowledge extraction is specific knowledge extraction, which automatically extracts the characteristic words and patterns based on hierarchy bootstrapping machine learning. A new method for joint entity and relation extraction using a graph called as a “card-pyramid”. This graph compactly encodes all possible entities and relations in a sentence, reducing the task of their joint extraction to jointly labeling its nodes. An efficient labeling algorithm that is analogous to parsing using dynamic programming. The experiment demonstrates the benefit of joint entity and relation extraction.