Razgovorni agent za korisničku podršku temeljen na dubokom učenju

master's thesis

• Title (english): Customer Support Chatbot Based on Deep Learning
• Author: Luka Dulčić
• Mentor: Jan Šnajder (mentor)
• Committee member: Jan Šnajder (predsjednik povjerenstva)
• Committee member: Marko Čupić (član povjerenstva)
• Committee member: Alan Jović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2018-07-16, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Virtualni razgovorni agenti chatbot u današnjem svijetu pronalaze sve više praktičnih primjena, jedna od tih je korištenje takvih razgovornih agenata u službi za korisnike. Ovaj rad implementira prototip virtualnog razgovornog agenta službe za korisnike pomoću modela strojnog učenja sekvenca u sekvencu. Funkcionalnost modela je evaluirana na nekoliko službi za korisnike te je iznesen osvrt na ovakve razgovorne agente.

Abstract (english)

Virtual conversational agents are nowadays finding more and more practical applications, one of those applications is customer support conversational agent. This paper implements a prototype of customer support conversational agent using machine learning sequence to sequence model. Model functionality is evaluated on several customer supports, also a general overview of customer support conversational agents is presented.

• Keywords: strojno učenje; obrada prirodnog teksta; neuronske mreže; duboko učenje; sekvenca u sekvencu; razgovorni agenti; virtualni razgovorni agenti; služba za korisnike; razgovorni agenti službe za korisnike
• Keywords (english): machine learning; natural language processing; neural networks; deep learning; sequence to sequence; conversational agents; virtual conversational agents; customer support; customer support conversational agents
• Language: croatian
• URN:NBN: urn:nbn:hr:168:289995
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-13 20:04:43