Topic Modelling of the Czech Supreme Court Decisions

D 2020

Topic Modelling of the Czech Supreme Court Decisions

NOVOTNÁ, Tereza; Jakub HARAŠTA a Jakub KÓL

Základní údaje

Originální název

Topic Modelling of the Czech Supreme Court Decisions

Autoři

NOVOTNÁ, Tereza; Jakub HARAŠTA a Jakub KÓL

Vydání

CEUR WS, vol. 2764. Aachen, Německo, Proceedings of the Fourth Workshop on Automated Semantic Analysis of Information in Legal Text held online in conjunction with the 33rd International Conference on Legal Knowledge and Information Systems (JURIX 2020), od s. 1-5, 5 s. 2020

Nakladatel

CEUR Workshop Proceedings

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

50501 Law

Stát vydavatele

Německo

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Odkazy

Open access sborníku

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14220/20:00117354

Organizační jednotka

Právnická fakulta

ISSN

EID Scopus

2-s2.0-85097601739

Klíčová slova anglicky

topic modelling; Latent Dirichlet Allocation; Non-negative Matrix Factorization; court decisions; coherence score

Štítky

rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 29. 3. 2021 16:05, Mgr. Petra Georgala

Anotace

V originále

The Czech Supreme Court produces significant amount of decisions totalling more than 130 000 decisions since 1993. The amount makes it difficult for law practitioners to research this case law. This work focuses on topic models for enhanced information retrieval through identification of case law approaching the same or similar issues. We provide initial quantitative evaluation of Latent Dirichlet Allocation (LDA) and Non-negative Matrix Factorization (NMF) models according to CV coherence score for different number of topics modelled n= {10, 20, ..., 90, 100}. Additionally, we provide qualitative evaluation for LDA and NMF models n= {20, 30} that will serve as a starting point for subsequent expert-user evaluation.

Návaznosti

MUNI/A/1454/2019, interní kód MU

Název: Automatické zpracování soudních rozhodnutí: experiment s uživateli

Investor: Masarykova univerzita, Automatické zpracování soudních rozhodnutí: experiment s uživateli, DO R. 2020_Kategorie A - Specifický výzkum - Studentské výzkumné projekty

Citovat

NOVOTNÁ, Tereza; Jakub HARAŠTA a Jakub KÓL. Topic Modelling of the Czech Supreme Court Decisions. Online. In Kevin D. Ashley, Katie Atkinson, L. Karl Branting, Enrico Francesconi, Matthias Grabmair, Vern R. Walker, Bernhard Waltl, Adam Zachary Wyner. Proceedings of the Fourth Workshop on Automated Semantic Analysis of Information in Legal Text held online in conjunction with the 33rd International Conference on Legal Knowledge and Information Systems (JURIX 2020). CEUR WS, vol. 2764. Aachen, Německo: CEUR Workshop Proceedings, 2020, s. 1-5. ISSN 1613-0073.

@inproceedings{1709636,
   author = {Novotná, Tereza and Harašta, Jakub and Kól, Jakub},
   address = {Aachen, Německo},
   booktitle = {Proceedings of the Fourth Workshop on Automated Semantic Analysis of Information in Legal Text held online in conjunction with the 33rd International Conference on Legal Knowledge and Information Systems (JURIX 2020)},
   edition = {CEUR WS, vol. 2764},
   editor = {Kevin D. Ashley, Katie Atkinson, L. Karl Branting, Enrico Francesconi, Matthias Grabmair, Vern R. Walker, Bernhard Waltl, Adam Zachary Wyner},
   keywords = {topic modelling; Latent Dirichlet Allocation; Non-negative Matrix Factorization; court decisions; coherence score},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Aachen, Německo},
   pages = {1-5},
   publisher = {CEUR Workshop Proceedings},
   title = {Topic Modelling of the Czech Supreme Court Decisions},
   url = {http://ceur-ws.org/Vol-2764/},
   year = {2020}
}

TY  - CONF
ID  - 1709636
AU  - Novotná, Tereza - Harašta, Jakub - Kól, Jakub
PY  - 2020
TI  - Topic Modelling of the Czech Supreme Court Decisions
PB  - CEUR Workshop Proceedings
CY  - Aachen, Německo
KW  - topic modelling
KW  - Latent Dirichlet Allocation
KW  - Non-negative Matrix Factorization
KW  - court decisions
KW  - coherence score
UR  - http://ceur-ws.org/Vol-2764/
L2  - http://ceur-ws.org/Vol-2764/
N2  - The Czech Supreme Court produces significant amount of decisions totalling more than 130 000 decisions since 1993. The amount makes it difficult for law practitioners to research this case law. This work focuses on topic models for enhanced information retrieval through identification of case law approaching the same or similar issues. We provide initial quantitative evaluation of Latent Dirichlet Allocation (LDA) and Non-negative Matrix Factorization (NMF) models according to CV coherence score for different number of topics modelled n= {10, 20, ..., 90, 100}. Additionally, we provide qualitative evaluation for LDA and NMF models n= {20, 30} that will serve as a starting point for subsequent expert-user evaluation.
ER  -

NOVOTNÁ, Tereza; Jakub HARAŠTA a Jakub KÓL. Topic Modelling of the Czech Supreme Court Decisions. Online. In Kevin D. Ashley, Katie Atkinson, L. Karl Branting, Enrico Francesconi, Matthias Grabmair, Vern R. Walker, Bernhard Waltl, Adam Zachary Wyner. \textit{Proceedings of the Fourth Workshop on Automated Semantic Analysis of Information in Legal Text held online in conjunction with the 33rd International Conference on Legal Knowledge and Information Systems (JURIX 2020)}. CEUR WS, vol. 2764. Aachen, Německo: CEUR Workshop Proceedings, 2020, s.~1-5. ISSN~1613-0073.

Přehled o publikaci