Your browser does not allow JavaScript!
JavaScript is necessary for the proper functioning of this website. Please enable JavaScript or use a modern browser.
Repository of the University of Ljubljana
Open Science Slovenia
Open Science
DiKUL
slv
|
eng
Search
Browse
New in RUL
About RUL
In numbers
Help
Sign in
Details
Gručenje z omejitvami na podlagi besedil in grafov pri razporejanju akademskih člankov
ID
Škvorc, Tadej
(
Author
),
ID
Robnik Šikonja, Marko
(
Mentor
)
More about this mentor...
,
ID
Lavrač, Nada
(
Comentor
)
PDF - Presentation file,
Download
(1,01 MB)
MD5: 9CDCB97C1E9FE56A4370B73CE2F37F52
PID:
20.500.12556/rul/0771c4e7-7814-410d-ab35-e43638033122
Image galllery
Abstract
Sestavljanje urnikov konference je časovno zahtevno opravilo. Urniki so sestavljeni iz različnih sej, na katerih so predstavljeni članki s skupnim raziskovalnim področjem ali podpodročjem. Ročno razporejanje člankov v urnik vzame veliko časa, saj je potrebno za vsak članek določiti, v katero področje spada. V magistrskem delu predstavimo metodo za avtomatizacijo tega postopka. Z uporabo metod strojnega učenja, obdelave naravnega jezika in analize omrežij poiščemo članke s skupno tematiko. Na podlagi podobnosti smo članke razvrstili v vnaprej definirane seje urnika z uporabo gručenja z omejitvami. Razvito metodo smo implementirali v sklopu spletne aplikacije. Za potrebe testiranja smo ustvarili podatkovno bazo znanstvenih člankov iz različnih konferenc strojnega učenja, ročno označenih z njihovim raziskovalnim podpodročjem. Vsak del metode smo testirali samostojno z različnimi pristopi, in dobili dobre rezultate. Celotno metodo smo testirali na člankih, izbranih za predstavitev na konferenci ECML-PKDD 2017. Dobili smo dobre rezultate, ki lahko služijo kot izhodišče za izgradnjo urnika konference.
Language:
Slovenian
Keywords:
obdelava naravnega jezika
,
analiza omrežij
,
gručenje
,
organizacija konferenc
Work type:
Master's thesis/paper
Organization:
FRI - Faculty of Computer and Information Science
Year:
2017
PID:
20.500.12556/RUL-95060
Publication date in RUL:
13.09.2017
Views:
1344
Downloads:
390
Metadata:
Cite this work
Plain text
BibTeX
EndNote XML
EndNote/Refer
RIS
ABNT
ACM Ref
AMA
APA
Chicago 17th Author-Date
Harvard
IEEE
ISO 690
MLA
Vancouver
:
ŠKVORC, Tadej, 2017,
Gručenje z omejitvami na podlagi besedil in grafov pri razporejanju akademskih člankov
[online]. Master’s thesis. [Accessed 5 June 2025]. Retrieved from: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=eng&id=95060
Copy citation
Share:
Secondary language
Language:
English
Title:
Text and Graph Based Constrained Clustering for Academic Paper Scheduling
Abstract:
Creating a conference schedule is a difficult task. Conference schedules consist of sessions, which contain papers that belong to the same field or subfield. Manually constructing such a schedule takes a lot of time, as each paper must be assigned to an appropriate subfield. This thesis presents a method for automating the schedule creation process. We use machine learning, natural language processing and network analysis to find papers with common research topics. Based on the similarities we group papers into predefined conference sessions using constrained clustering. We implemented the method as a part of a web application. To test the proposed method we created a database of academic papers from several machine learning conferences and labeled them manually with their research subfield. We tested each part of the method independently and obtained good results. The full method was tested on papers accepted to the ECML-PKKD 2017 conference. We obtained useful results that can be used as a starting point when creating a conference schedule.
Keywords:
natural language processing
,
network analysis
,
clustering
,
conference organization
Similar documents
Similar works from RUL:
Conference paper scheduling tool
Automated Analysis and Emotion-based Classification of Music Lyrics
Device reconstruction based on KNX project file
Semantics-based automated essay evaluation
Efficient natural language processing with Python
Similar works from other Slovenian collections:
SEO optimization tool
IMPLEMENTATION OF A VIRTUAL AGENT USING OPEN-SOURCE VERBOT ENGINE
Evaluation of machine learning methods with natural language processing
Using words from daily news headlines to predict the movement of stock market indices
Machine learning based analysis of scientific journals and authors
Back