Formulation of Relation Entities using Context-Based Approach

  Sheeba S,  Vijayalakshmi M

Relation Extraction is a tedious process in an environment where there is no information present for binding of related data. Even if the data is extracted in that environment, it is difficult to prove that the extracted information is truthful. In order to overcome this drawback, a method called context-based approach is proposed which attempts to prove the truthfulness of the extracted data. The proposed technique strives to achieve Connection completion (RC) criterion which is the serious drawback with the existing approach. This approach is built by identifying certain terms called key terms from the user request and grouping them as entities. These entities are then framed as individual incomplete instance pairs. Depending upon the instance pairs specific queries are generated based on the proposed context based approach. The query is given with some test data for better accuracy of the retrieved relations. Hence Connection completion is achieved and the retrieved relation will have better precision and recall in comparison with existing approach. The results were obtained based on real time dynamic data gathered and grouped into data sets.

Keywords- Relation Entity, Natural language processing, relation extraction, context

Unique Identification Number - IJEDR1502038
Page Number(s) - 206-211
Pubished in - Volume 3 | Issue 2 | May 2015
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  Sheeba S,  Vijayalakshmi M,   "Formulation of Relation Entities using Context-Based Approach", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.3, Issue 2, pp.206-211, May 2015, Available at :http://www.ijedr.org/papers/IJEDR1502038.pdf