< Home
Logo

Create
TitleCategoryDescription Created atMaintainer

21-30 / 30 show all
EvaluatorEvaluation Description Evaluator is a module to evaluate given question answering system, based on the user's choice of modules. Users can make use of configuration options to choose which modules to use for the steps of QA system. Once evalutor runs, it sends a natural language question in answer dataset to Controller one-by-one. It compares true answer of the dataset with the answer list from Controller to calculate accuracy of the system. Function Evaluator evaluates the overall QA system using answer set. For instance, let the answer set contains only two sentences, "Which rivers flow through Seoul?" and "Who is the author of 'Samguk Sagi'?" In addition, suppose that Controller success to give correct answer for the former question, but fails for the latter one. Then, Evaluator would return accuracy 1/2 = 0.5 to the user. Scope and limit The only dataset usable for the Evalator is NLQ-1 dataset, which contains question-answer pair for only Korean and English at the moment (March, 2016) with 40 questions in the set. Since Evaluator works for measuring accuracy of the given QA system, it is not suitable for analyzing each test case. For the purpose, you may use website for Controller or website for Evaluator (which supports dump file for each question). Issues and discussion * Is it possible to make use of another answer set like QALD-4? Not yet (January 13, 2016, OKBQA3.5). However, supporting mult-answer sets would be added at OKBQA4(http://4.okbqa.org) * Can I test my own QA system? Since Evaluator calls Controller to retrieve answers of each questions, only QA system following OKBQA system structure (TGM, DM, AGM) is applicable. This structure is targetted for those who want to add their own modules to the OKBQA system structure, and checks the performance of it. Maintainer: Sang-min An {asm427@kaist.ac.kr}2016-01-13 16:26:23 UTCasm427@kaist.ac.kr
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
SparqlatorQuery generation Description It is a wrapper to call the GraphFinder::sparqlator method, using the OKBQA framework API. It takes a template and a disambiguation structures which are produced by a template generation and a disambiguation modules, respectively, and produces a set of SPARQL queries which are supposed to represent the same query need represented by the template and disambiguation. Optionally, the parameter, max_hop may be set to specify the number of maximum hops for each path to be extended to. As it is to specify an integer value (between 1 and 3, usually), it may be simply encoded in the URL (see Web service URL example below). GraphFinder implements the triple variation operations proposed by [1]. Scope and limit The current version implements only the three operations, inversion, split, and instantiation, among the four proposed in [1]. Implementation of the last one, join is remained as a future work. Language dependency GraphFinder is language-independent, and so does the sparqlator module. References Jin-Dong Kim and Kevin Bretonnel Cohen, “Triple Pattern Variation Operations for Flexible Graph Search”, Proceedings of the 1st international workshop on Natural Language Interfaces for Web of Data (NLIWoD), 2014. 2015-08-28 00:33:26 UTCjindong.kim@gmail.com
C2K 2.0Other C2K is a knowledge acquisition system that extracts triples of DBpedia properties from DBpedia category triples. C2K is proposed by Jiseong Kim, et al., "The Association Rule Mining System for Acquiring Knowledge of DBpedia from Wikipedia Categories", NLP & DBpedia @ ISWC, 2015. 2015-11-24 06:05:14 UTCjiseong@kaist.ac.kr
StarGraph Disambiguation Module Disambiguation Disambiguation module which uses distributional semantics for mapping terms to entities.2016-07-21 02:17:27 UTCandrenfreitas@gmail.com
Web InterfaceRendering OKBQA Web User Interface2016-06-24 01:07:19 UTCwiany11@kaist.ac.kr
DM Python WrapperDisambiguation This is a disambiguation module wrapper for python programmers. In the codes, it takes a input by RESTful API and checks whether it is the right form of an input of DM. The following of the codes are for programmers to implement their own disambiguation logic. The last of the codes takes an output from the results of programmers' logic and checks whether it is the right form of an DM output, and then returns it to clients by RESTful API.2016-06-24 07:16:17 UTCjiseong@kaist.ac.kr
TGM Python WrapperTemplate generation This is a template generation module wrapper for python programmers. In the codes, it takes a input by RESTful API and checks whether it is the right form of an input of TGM. The following of the codes are for programmers to implement their own template generation logic. The last of the codes takes an output from the results of programmers' logic and checks whether it is the right form of an TGM output, and then returns it to clients by RESTful API.2016-06-24 07:15:49 UTCjiseong@kaist.ac.kr
Controller 1.1.5Control This module links the inputs and outputs of all modules (template generation modules, disambiguation modules, query generation modules) and returns final answers of an input question string using an answer generation module embedded in the control module. This module supports the address configuration of each module and SPARQL endpoints. The controller 1.1.5 is enhanced version of the initial controller w.r.t. concurrency control and load control. The capability of load control is achieved by adjusting the number of answers to be returned by the additional configuration field ("answer_num"). By adjusting the number of answers, testers can trade off the output time against the output size.2016-01-13 15:31:24 UTCjiseong@kaist.ac.kr
Create