Professional Documents
Culture Documents
A Syntactic and Semantic Multi-Agent Based Question Answering System For Collaborative E-Learning 2018
A Syntactic and Semantic Multi-Agent Based Question Answering System For Collaborative E-Learning 2018
Abstract— with the rapid progress in technology and the the answer in form of parts of textbooks or hyperlinks to
advancement in learning systems, e-Learning has proved to be
one of the best means for learning in many sectors. In an e- documents containing the answers, which is inconvenient for
Learning environment, and to help learners to benefit the the students or learners.
maximum from their courses, tutors are faced with the arduous In this paper we present a syntactic and semantic multi-
task of writing answers —containing detailed, useful agent approach to question answering in e-learning platforms.
information— to every query and question they receive daily
Our proposal is to improve existing approaches ([3], [4]) by
from their students. The task can take up a considerable amount
presenting an architecture composed of three layers: (1) user
of the time they spend each day on teaching if the number of
students is high and the tutors have a narrow timeframe in which
layer, (2) Answer Finding layer, and (3) Data base layer. First,
to reply to them all. the user layer receives the question (vocal or text) and send it
to the Answer Finding layer, where different agents analyze the
In this paper, we present a Question Answering System question and search for the best answer from all the available
(QAS) that helps learners to find the best answers to their resources (Q/A bank, courses BD, Internet) and communicate
questions and helps tutors to answer questions asked by their with the tutor or other learners if needed.
students in an e-Learning environment. we present a syntactic
This approach allows the use of different strategies and the
and semantic multi-agent approach to question answering in e-
learning platforms. We try to improve existing approaches by
reduction of errors introduced by individual methods. The
using multiple techniques in a multi-layer system where learners cooperation among the agents aims to reach better solutions in
and tutors with the help of automatic agents collaborate to find each step of the processing.
the best answer to the submitted question.
II. QUESTION ANSWERING SYSTEMS (QAS)
Keywords— Multi-Agent System; Question Answering
System; semantic web, collaborative e-Learning, Ontology. The QASs play an important role in the process of an e-
Learning course, by helping the learners to achieve the end of
the course without a problem and by finding the best answers
I. INTRODUCTION to their questions. But the challenge is that the questions in an
A Question Answering (QA) is a type of information e-Learning environment are considered more complex as they
retrieval. Given a collection of documents (such as the World require a source/domain knowledge and also long answers
Wide Web or a local collection) the system should be able to require to be extracted from multiple documents. Therefore,
retrieve answers to questions posed in natural language. QA is there are many QASs architectures that uses different methods
regarded as requiring more complex natural language and techniques. In [3] T.Alinaghi, et al. introduce a multi agent
processing (NLP) techniques than other types of information approach to Question Answering that applies all available
retrieval such as document retrieval, and it is sometimes resources to find answers to questions, three types of resources
regarded as the next step beyond search engines. QA research are used Frequently Asked Questions (FAQ) , course materials
attempts to deal with a wide range of question types including: and answers by other learner. In [5] Chun-Chia Wang and C.
fact, list, definition, how, why, hypothetical, semantically- Hung introduce a semantic-based automated (QA) system like
constrained and cross-lingual questions [1][2]. a virtual teacher to respond to student questions online. In [6]
V. Lopez et al. present AquaLog as an ontology-driven
A Question Answering system (QAS) is an important tool question-answering system which takes queries expressed in
for improving e-learning and education. Several approaches natural language and an ontology as input, and returns answers
employ different technologies to understand questions given in drawn from one or more knowledge bases (KBs). In [7] P.
natural language text and after analyzing the question returns Malhotra et al. focuses on creating semantic analyzer for
automatic Question-answering system for domain specific
C. Database layer :
This layer contain the different databases needed to
generate the answer, it is composed of:
• Questions/Answers bank,
• Courses Profiles Database,
• Courses Documents Database,
• learners Profiles Database
• Metadata database.