A Chatbot as a Natural Web Interface to Arabic Web QA
In this paper, we describe a way to access Arabic Web Question Answering (QA) corpus using a chatbot, without the need for sophisticated natural language processing or logical inference. Any Natural Language (NL) interface to Question Answer (QA) system is constrained to reply with the given answers...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Kassel University Press
2011-03-01
|
Series: | International Journal of Emerging Technologies in Learning (iJET) |
Subjects: | |
Online Access: | http://online-journals.org/i-jet/article/view/1502 |
id |
doaj-25ea35e58e7b46a8b38c983ab9a86106 |
---|---|
record_format |
Article |
spelling |
doaj-25ea35e58e7b46a8b38c983ab9a861062020-11-24T21:25:03ZengKassel University PressInternational Journal of Emerging Technologies in Learning (iJET)1863-03832011-03-0161374310.3991/ijet.v6i1.1502A Chatbot as a Natural Web Interface to Arabic Web QABayan Abu ShawarIn this paper, we describe a way to access Arabic Web Question Answering (QA) corpus using a chatbot, without the need for sophisticated natural language processing or logical inference. Any Natural Language (NL) interface to Question Answer (QA) system is constrained to reply with the given answers, so there is no need for NL generation to recreate well-formed answers, or for deep analysis or logical inference to map user input questions onto this logical ontology; simple (but large) set of pattern-template matching rules will suffice. In previous research, this approach works properly with English and other European languages. In this paper, we try to see how the same chatbot will react in terms of Arabic Web QA corpus. Initial results shows that 93% of answers were correct, but because of a lot of characteristics related to Arabic language, changing Arabic questions into other forms may lead to no answers. http://online-journals.org/i-jet/article/view/1502chatbotinformationretrievalquestionansweringsystem |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Bayan Abu Shawar |
spellingShingle |
Bayan Abu Shawar A Chatbot as a Natural Web Interface to Arabic Web QA International Journal of Emerging Technologies in Learning (iJET) chatbot information retrieval question answering system |
author_facet |
Bayan Abu Shawar |
author_sort |
Bayan Abu Shawar |
title |
A Chatbot as a Natural Web Interface to Arabic Web QA |
title_short |
A Chatbot as a Natural Web Interface to Arabic Web QA |
title_full |
A Chatbot as a Natural Web Interface to Arabic Web QA |
title_fullStr |
A Chatbot as a Natural Web Interface to Arabic Web QA |
title_full_unstemmed |
A Chatbot as a Natural Web Interface to Arabic Web QA |
title_sort |
chatbot as a natural web interface to arabic web qa |
publisher |
Kassel University Press |
series |
International Journal of Emerging Technologies in Learning (iJET) |
issn |
1863-0383 |
publishDate |
2011-03-01 |
description |
In this paper, we describe a way to access Arabic Web Question Answering (QA) corpus using a chatbot, without the need for sophisticated natural language processing or logical inference. Any Natural Language (NL) interface to Question Answer (QA) system is constrained to reply with the given answers, so there is no need for NL generation to recreate well-formed answers, or for deep analysis or logical inference to map user input questions onto this logical ontology; simple (but large) set of pattern-template matching rules will suffice. In previous research, this approach works properly with English and other European languages. In this paper, we try to see how the same chatbot will react in terms of Arabic Web QA corpus. Initial results shows that 93% of answers were correct, but because of a lot of characteristics related to Arabic language, changing Arabic questions into other forms may lead to no answers. |
topic |
chatbot information retrieval question answering system |
url |
http://online-journals.org/i-jet/article/view/1502 |
work_keys_str_mv |
AT bayanabushawar achatbotasanaturalwebinterfacetoarabicwebqa AT bayanabushawar chatbotasanaturalwebinterfacetoarabicwebqa |
_version_ |
1725985198783332352 |