Implementacija automatiziranog sustava za generalni tekstualni razgovor (eng. chatbot)

master's thesis

• Title (english): Implementation of an automated system for general text chat (chatbot)
• Author: Iva Tutiš
• Mentor: Matej Mihelčić (mentor)
• Committee member: Matej Mihelčić (predsjednik povjerenstva)
• Committee member: Boris Muha (član povjerenstva)
• Committee member: Marko Radulović (član povjerenstva)
• Committee member: Matija Bašić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Science; (Department of Mathematics); Zagreb
• Defense date and country: 2022-11-30, Croatia
• Scientific / art field, discipline and subdiscipline: NATURAL SCIENCES; Mathematics

Abstract

U ovom radu smo opisali koncept chatbota, to jest sustava za automatizirani generalni tekstualni razgovor sa ljudskim korisnikom. Usredotočili smo se na dizajn dva chatbota u jezicima Java i Python sa pratećim tehnologijama i bibliotekama koje implementiraju algoritme za procesiranje prirodnog jezika (NLP) algoritme i algoritme dubokog učenja. Nakon implementacije chatbota, programe smo testirali i prokomentirali njihove preformanse.

Abstract (english)

In this thesis, we described the concept of a chatbot, a software designed for automated conversation with a live human agent. We focused on designing two chatbots using Java and Python programming languages with accompanying technologies and libraries that implement natural language processing (NLP) algorithms and deep learning algorithms. After implementing the chatbota, we tested them and commented on their preformance.

• Keywords: automatizirani generalni tekstualni razgovor; ljudski korisnik; chatbot; Java; Python; algoritmi za procesiranje prirodnog jezika; (NLP) algoritmi; algoritmi dubokog učenja
• Keywords (english): software designed for automated conversation; live human agent; chatbots; Java programming language; Python programming language; natural language processing (NLP) algorithms; deep learning algorithms
• Language: croatian
• URN:NBN: urn:nbn:hr:217:751103
• Study programme: Title: Computer Science and Mathematics; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra računarstva i matematike (magistar/magistra računarstva i matematike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2022-12-20 13:17:36