< Home
Logo

Create
TitleCategoryDescriptionCreated atMaintainer

21-30 / 30 show all
Answerer 2016Answer generation Main changes It is slightly changed to coherent to controller 2016. Some optimization has been adapted. Limitations Query processing speed (Now resolved) Not yet, AGM 2016 uses scores to prune SPARQL queries to reduce the search space. Currently, the processing time of the entire pipeline is the one of the main issues. In the next version, it can be considered to use of scores to boost up the processing speed. 2016-08-08 06:00:32 UTCjiseong@kaist.ac.kr
SRDF 1.0Other Description SRDF is a Korean Open Information Extraction system. It is designed to meet the characteristics of Korean and extract multiple relationships between argument(s) and relation(s) within a sentence by using reificaion technique(specifically, singleton property method). It takes a sentence and produces a set of reified triples on lexical format. Scope and limit The current version covers sentences composed from 3 to 10 words. To eliminate restriction of word length, a new version is being developed. References 1. Sangha Nam, et. al., "SRDF: Korean Open Information Extraction using Singleton Property", ISWC (Poster) 2015.2015-11-05 07:44:01 UTCnam.sangha@gmail.com
TGM JAVA WRAPPERTemplate generation Description It is a wrapper for Java Template Generation Module(TGM). If you want to develop a new TGM module, you can use it as a template for OKBQA pipeline. Because it has a function for format validation of input and output, and is also developed using REST API. The sample input and output are written by Korean. But you can also using by English. 2016-01-13 10:40:32 UTCnam.sangha@gmail.com
DM JAVA WRAPPERDisambiguation Description It is a warpper for Java Disambiguation Module(DM). If you want to develop a new DM module, you can use it as a template for OKBQA pipeline. Because it has a function for format validation of input and output, and is also developed using REST API. The sample input and output are written by Korean. But you can also using by English.2016-01-13 10:42:28 UTCnam.sangha@gmail.com
En-Ko Local KB 2015Other # DBpedia local endpoint URI http://143.248.135.20:45103/sparql # Graph IRI # English DBpedia http://en.dbpedia2015-04.kaist.ac.kr http://en.dbpedia2015-10.kaist.ac.kr # Korean DBpedia http://ko.dbpedia2015-10.kaist.ac.kr http://ko.dbpedia2015.kaist.ac.kr 2016-06-23 02:16:22 UTCnam.sangha@gmail.com
KO TGM 2016Template generation Description SenTGM is a SRDF-based Korean Template Generation module for generating SPARQL template from natural language question. SPARQL template follows 'templator' module made by christina unger. Function 1. Translate natural language question to declarative sentence by rules. 2. Run SRDF module for this declarative sentence. 3. Convert SRDF output to SPARQL template. Scope and Limit Translating NLQ to DS is developed very simple. If translate-sub-module is developed better, the overall performance will be raise. References 1. Sangha Nam, et. al., "SRDF: Korean Open Information Extraction using Singleton Property", ISWC (Poster) 2015.2016-07-21 02:26:02 UTCnam.sangha@gmail.com
ELU-KoOther # 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}2016-03-05 06:58:19 UTCprismriver@kaist.ac.kr
Korean DMDisambiguation # Description Korean DM is the first version of Korean Disambiguation Module. It uses pre-defined attributes and ELU to disambiguate property & entities # Function Korean DM find corresponding entities and properties from the output of TGM. Based on the given information it tried to find the best matching for verbalized variables. The result is returned as three categories (properties / classes / entities) with its variables. # Scope and limit Korean DM only disambiguates properties and entities. It does not work for finding correct classes at the moment. The program would be updated to handle lexicaly associated properties, and filter properties that could not make result according to the given template # Language Dependency It only supports Korean text. (July 21, 2016, OKBQA4). Maintainer: Jeong-uk Kim {prismriver@kaist.ac.kr}2016-07-21 05:01:15 UTCprismriver@kaist.ac.kr
Web InterfaceRendering OKBQA Web User Interface2016-06-24 01:07:19 UTCwiany11@kaist.ac.kr
AGDISTIS-KODisambiguation # Description Disambiguator uses the AGDISTIS web service to disambiguate URIs for class, property and resources, and then maps them within the result of Templator. So, for the Korean Disambiguator, anyone can use this module. I/O is exactly same with AGDISTIS-en. # Function AGDISTIS-ko works as a sub-module of Disambiguator. It works to disambiguate the URIs for each entities. # Scope and limit Currently (March, 2016), AGDISTIS-ko's algorithm is exactly same with AGDISTIS-en's. It works for Korean, and disambiguates entites within DBpedia URIs # Issues and discusion * Do you want to develop Korean Disambiguator? If you want, there are two remaining development issue. 1. The NER module including this processe: NER and generate the output as well as the input of AGDISTIS-ko (you can see the example) 2. The Wrapper module: Input: Templator output Output: Disambiguator output * How to run the service $ cd /home/b11_2015/AGDISTIS-ko/AGDISTIS $ mvn exec:java Maintainer: Younggyun Hahm {hahmyg@kaist.ac.kr}2015-08-28 06:30:36 UTCzakria.ai@gmail.com
Create