< Home


Category Other

# Description

ELU-Ko is a module to find entities in Koren text.
Based on the labels of the Dbpedia entities, the ELU-Ko module finds entity candidates in the given text.
Then, it chooses entities among the candidates based on the scores of them.

# Function

ELU-Ko finds Korean Dbpedia entities in the given natural langauge text. For instance, suppose sentence "대한민국의 지방법원의 수는 총 18개이다." is given as input.
We can find out that '대한민국' correspond to the entity http://ko.dbpedia.org/page/대한민국, that '지방법원' corresponds to http://ko.dbpedia.org/page/지방법원, and so on.
The found entitie are returned as list for the output of the module.

# Scope and limit

ELU-Ko uses entities' disambiguation, redirection, and labels candidate choice.
Therefore, those that is not mentioned in the Dbpedia cannot be found using the ELU-Ko. In addition, although ELU-Ko makes use of confidential score of label as well as neighboring entity candidates, there still exists several errors.

# Language Dependency

It only supports Korean text. (January 13, 2016, OKBQA3.5).
However, the algorithm is independent to the language, and the coverage would be extended at OKBQA4(http://4.okbqa.org)
You may use AGDIST for English entity detecton.

Developer: Youngsik Kim {twilight@kaist.ac.kr}
Maintainer: Jeong-uk Kim {prismriver@kaist.ac.kr}
Maintainer prismriver@kaist.ac.kr
Source-code URL
Homepage URL
Web service URL
Sample cURL command curl -X POST -H "Content-Type:application/json" -d '_sample_input_' Test
Sample input
Sample output