Skip to content
/ ScoQAS Public

A collection of samples for Semantic closed and open domain Question Answering System (ScoQAS) to find out the structure of the question syntactically and semantically through integrating NLP methods allowing a deep analysis of questions and exploiting of semantic based approach.

Notifications You must be signed in to change notification settings

mlatifi/ScoQAS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

64 Commits
 
 
 
 
 
 

Repository files navigation

Semantic-based closed and open domain Question Answering System (ScoQAS) Architecture [Beta]:

In the ScoQAS architecure, there are common and specific components, modules, and KBs. This is the repository of the Ontology Based Question Answering System which process the NL questions. The ScoQA system is based on NLP techniques combining semantic-based structure-feature patterns (Ss-fP) for question classification and creating a question syntactic-semantic information structure (QSiS). The ScoQA system performs over ontologies not over free text and operates on two scenarios, one Closed-domain, where the domain is restricted by an ontology, which using a human-made ontology and the other is Open domain where the answers are retrieved from a LOD knowledge base.

There are common and specific components, modules, and KBs. Some of these components are such as Question Preprocessing, Question Representation, Question Classifier, Building Constraints, Graph Construction, SPARQL Query Construction and Answer Extraction.

You can use these samples as a reference or as a starting point for creating your own apps. The focus here is on code structure, architecture, testing and maintainability. However, bear in mind that there are many ways to build apps with these architectures and tools, depending on your priorities, so these shouldn't be considered canonical examples.

Each components are released in their own branch. Check each componets's README for more information.

Component samples:

This project is built by Majid Latifi . I developed ScoQAS for modeling and gathering data when following a certain theory/methodology in Articial Intelligence. Please cite these papers when you are using this code:

1- Latifi, M., Rodríguez, H., & Sànchez-Marrè, M. (2017). ScoQAS: A Semantic-based Closed and Open Domain Question Answering System. Procesamiento del Lenguaje Natural, 59, 73-80.

2- Latifi, M., & Sànchez-Marrè, M. (2013, October). The Use of NLP Interchange Format for Question Answering in Organizations. In CCIA (pp. 235-244).

License:

About

A collection of samples for Semantic closed and open domain Question Answering System (ScoQAS) to find out the structure of the question syntactically and semantically through integrating NLP methods allowing a deep analysis of questions and exploiting of semantic based approach.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages