NOVOTNÁ, Tereza, Jakub HARAŠTA and Jakub KÓL. Topic Modelling of Czech Supreme Court Decisions repository. GitHub, 2020.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Topic Modelling of Czech Supreme Court Decisions repository
Authors NOVOTNÁ, Tereza, Jakub HARAŠTA and Jakub KÓL.
Edition 2020.
Publisher GitHub
Other information
Original language English
Type of outcome Special-purpose publication
Field of Study 50501 Law
Country of publisher United States of America
Confidentiality degree is not subject to a state or trade secret
WWW open source models: github repository open source codes: github repository
Organization unit Faculty of Law
Keywords (in Czech) topic modelling; latent Dirichlet allocation; non-negative matrix factorization; court decisions; coherence score
Tags International impact
Changed by Changed by: Mgr. Tereza Novotná, Ph.D., učo 421694. Changed: 26/1/2021 17:15.
Abstract
This is Topic Modelling of Czech Supreme Court Decisions repository containing all the relevant data and code for the topic modelling of the Czech Supreme Court decisions with latent Dirichlet allocation (LDA) and non-negative matrix factorization (NMF) methods. This repository contains 5 Jupyter notebooks with all the relevant code for preprocessing of documents, training the models and their topics visualization via pyLDAvis using LDA and NMF methods.
Links
MUNI/A/1454/2019, interní kód MUName: Automatické zpracování soudních rozhodnutí: experiment s uživateli
Investor: Masaryk University, Category A
PrintDisplayed: 20/7/2024 03:22