ParsyBot: Chatbot for Baskent University Related FAQs

dc.contributor.authorKarkiner, Zeynep
dc.contributor.authorYaman, Begum
dc.contributor.authorZengin, Begum
dc.contributor.authorCavli, Feride Nursena
dc.contributor.authorSert, Mustafa
dc.date.accessioned2025-05-06T07:25:32Z
dc.date.issued2024-05-17
dc.description.abstractReading regulations and instructions may take lots of time and sometimes it results in disappointments. To avoid this issue, people are prone to use sources that provide fast and accurate answers while accessing the information. Chatbots, are one of the most popular trend topics nowadays, and may adapted into various fields e.g., healthcare, finance, and education. This paper proposes the development of ParsyBot which is a Turkish chatbot designed to inform users about the regulations, admissions, departments, scholarships, and social clubs of Baskent University. Furthermore, users may ask via voice in Turkish this feature is not common among the other chatbots. ParsyBot uses a pre-trained BERT model which is specifically trained with regulations and instructions of Baskent University. Parsybot runs on web and mobile platforms to make it available for everyone. Our experiments on the utilized dataset, ParsyBot, reached 0.81 in METEOR, and 0.24 in ROGUE-1, which are promising compared to the ChatGPT 3.5.
dc.identifier.issn2325-6516
dc.identifier.scopus2-s2.0-85192263262
dc.identifier.scopus2-s2.0-85188821079
dc.identifier.urihttps://hdl.handle.net/11727/12966
dc.identifier.wos001196221400026
dc.identifier.wos001208593400005
dc.language.isoen_US
dc.publisher18TH IEEE INTERNATIONAL CONFERENCE ON SEMANTIC COMPUTING, ICSC 2024
dc.subjectChatbot
dc.subjectBERT
dc.subjectNLP
dc.subjectMobile Application
dc.titleParsyBot: Chatbot for Baskent University Related FAQs
dc.typeOther

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Kapalı Erişim.pdf
Size:
78 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: