magistrsko delo
Matevž Pavlič (Author), Matej Guid (Mentor)

Abstract

Argumentirano strojno učenje (angl. argument-based machine learning, ABML) omogoča interakcijo med metodo strojnega učenja in ekspertom v izbrani domeni ter z njo elicitacijo znanja iz domenskega eksperta. Ekspert pojasni samo skrbno izbrane kritične" primere in tako na hiter in učinkovit način podaja le relevantno znanje. ABML lahko uporabimo tudi kot inteligentni sistem za poučevanje, temelječem na argumentiranju. S podajanjem povratne informacije o kvaliteti podanega argumenta lahko efektivnost podajanja znanja še povečamo. V delu smo zasnovali in implementirali 2 meri za ocenjevanje argumentov. Evalvacijo mer (2 novi, 1 obstoječa) smo izvedli v sklopu ABML postopka pri gradnji napovednega modela za napovedovanje bonitetnih ocen podjetjem. Eksperiment je vseboval dva dela, elicitacijo znanja iz učitelja in elicitacijo znanja iz učenca. V prvem delu s pomočjo finančnega eksperta dosežemo konsistenten nabor podatkov in uvedbo naprednejših konceptov, ki opisujejo domeno. Drugi del predstavlja učno sejo, v kateri se učenec spozna z domeno in nauči razumevanja konceptov preko interaktivne učne zanke. V izvedbi postopka z učenci se je ena izmed razvitih mer izkazala za posebej uspešno.

Keywords

inteligentni tutorski sistemi;interaktivna zanka za zajemanje znanja s pomočjo argumentiranega strojnega učenja;na argumentiranju temelječe interaktivno učno orodje;ocenjevanje kvalitete argumentov;finančna analiza;napovedovanje bonitetnih ocen podjetij;računalništvo;računalništvo in informatika;magisteriji;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [M. Pavlič]
UDC: 004.85(043.2)
COBISS: 1536298179 Link will open in a new window
Views: 1553
Downloads: 534
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Estimating the quality of arguments in argument-based machine learning
Secondary abstract: Argument-based machine learning (ABML) enables an interaction between a machine learning algorithm and an expert in a given domain, in order to achieve successful knowledge elicitation from the domain expert. The expert provides knowledge in a quick and efficient way by explaining only automatically chosen critical" examples. ABML can also be used as an argumentation-based teaching tool. By providing more information about the quality of the given arguments, we can improve the effectiveness of the knowledge elicitation. In our thesis, we have designed and implemented two measures for estimating the quality of arguments. Evaluation of measures (2 new, 1 existent) was done through an ABML procedure, where we learned a classification model for predicting the credit score of companies. Experiment consisted of two parts: knowledge elicitation from the teacher, and knowledge elicitation from the student. The goal of the first part was to obtain a consistent data set and introduction of advanced concepts, that describe the domain. This was done with the help of a financial expert. The second part was the tutoring session, where the student learned the intricacies of the domain and achieved comprehension of the advanced concepts, by means of using the interactive tutoring loop. While carrying out the teaching trials with the students, one measure proved to be particularly successful.
Secondary keywords: intelligent tutoring systems;argument-based machine learning knowledge refinement loop;argumentation-based interactive teaching tool;estimating the quality of arguments;financial analysis;credit scoring;computer science;computer and information science;master's degree;
File type: application/pdf
Type (COBISS): Master's thesis/paper
Study programme: 1000471
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 79 str.
ID: 8751949