User Interface for a Template Based Question Answering System

Author(s):  
Konrad Höffner ◽  
Christina Unger ◽  
Lorenz Bühmann ◽  
Jens Lehmann ◽  
Axel-Cyrille Ngonga Ngomo ◽  
...  
Author(s):  
Andrew J. Cowell ◽  
Alan R. Chappell ◽  
David A. Thurmanb

Battelle is working in partnership with Stanford University's Knowledge Systems Laboratory (KSL) and IBM's T.J. Watson Research Center to develop a suite of technologies for knowledge discovery, knowledge extraction, knowledge representation, automated reasoning, and human information interaction, in unison entitled “Knowledge Associates for Novel Intelligence” (KANI). We have developed an integrated analytic environment composed of a collection of analyst associates, software components that aid the analyst at different stages of the analytical process. In this paper, we discuss our efforts in the research, design and implementation of the question answering elements of the Information Interaction Associate. Specifically, we focus on the techniques employed to produce an effective user interface to these elements. In addition, we touch upon the methodologies we intend to use to empirically evaluate our approach with active intelligence analysts.


2021 ◽  
Author(s):  
García-Robledo Gabriela A ◽  
Reyes-Ortiz José A ◽  
González-Beltrán Beatriz A ◽  
Bravo Maricela

The development of question answering (QA) systems involves methods and techniques from the areas of Information Extraction (EI), Natural Language Processing (NLP), and sometimes speech recognition. A user interface that involves all these tasks requires deep development to improve the interaction between a user and a device. This paper describes a Spanish QA system for an academic domain through a multi-platform user interface. The system uses a voice query to be transformed into text. The semi-structured query is converted into SQWRL language to extract a system of ontologies from an academic domain using patterns. The answer of the ontologies is placed in templates classified according to the type of question. Finally, the answer is transformed into a voice. A method for experimentation is presented focusing on the questions asked in voice and their respective answers by experts from the academic domain in a set of 258 questions, obtaining a 92% accuracy.


Sign in / Sign up

Export Citation Format

Share Document