Human Evaluation Experiment of Legal Information Retrieval
Methods

D 2021

Human Evaluation Experiment of Legal Information Retrieval Methods

NOVOTNÁ, Tereza

Základní údaje

Originální název

Human Evaluation Experiment of Legal Information Retrieval Methods

Autoři

NOVOTNÁ, Tereza

Vydání

vol. 346. Amsterdam, Berlin, Washington, DC, Frontiers in Artificial Intelligence and Applications, Vol. 346 Legal Knowledge and Information Systems. Proceedings of JURIX 2021. od s. 131-137, 7 s. 2021

Nakladatel

IOS Press

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

50501 Law

Stát vydavatele

Nizozemské království

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/00216224:14220/21:00123262

Organizační jednotka

Právnická fakulta

ISBN

978-1-64368-252-5

ISSN

Klíčová slova anglicky

human evaluation; court decisions retrieval; doc2vec; citation analysis; LDA; multilayered approach

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 20. 6. 2024 16:14, Mgr. Tereza Novotná, Ph.D.

Anotace

V originále

In this article, I present the results of the human evaluation experiment of three commonly used methods in legal information retrieval and a new ”multilayered” approach. I use the doc2vec model, citation network analysis and two topic modelling algorithms for the Czech Supreme Court decisions retrieval and evaluate their performance. To improve the accuracy of the results of these methods, I combine the methods in a ”multilayered” way and perform the subsequent evaluation. Both evaluation experiments are conducted with a group of legal experts to assess the applicability and usability of the methods for legal information retrieval. The combination of the doc2vec and citations is found satisfactory accurate for practical use for the Czech court decisions retrieval.

Návaznosti

CZ.02.2.69/0.0/0.0/19_073/0016943, interní kód MU
(Kód CEP: EF19_073/0016943)

Název: Interní grantová agentura Masarykovy univerzity (Akronym: IGA MU)

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Interní grantová agentura Masarykovy univerzity, PO 2 Rozvoj vysokých škol a lidských zdrojů pro výzkum a vývoj

Citovat

NOVOTNÁ, Tereza. Human Evaluation Experiment of Legal Information Retrieval Methods. Online. In Erich Schweighofer. Frontiers in Artificial Intelligence and Applications, Vol. 346 Legal Knowledge and Information Systems. Proceedings of JURIX 2021. vol. 346. Amsterdam, Berlin, Washington, DC: IOS Press, 2021, s. 131-137. ISBN 978-1-64368-252-5. Dostupné z: https://doi.org/10.3233/FAIA210328.

@inproceedings{1810038,
   author = {Novotná, Tereza},
   address = {Amsterdam, Berlin, Washington, DC},
   booktitle = {Frontiers in Artificial Intelligence and Applications, Vol. 346 Legal Knowledge and Information Systems. Proceedings of JURIX 2021.},
   doi = {https://doi.org/10.3233/FAIA210328},
   edition = {vol. 346},
   editor = {Erich Schweighofer},
   keywords = {human evaluation; court decisions retrieval; doc2vec; citation analysis; LDA; multilayered approach},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Amsterdam, Berlin, Washington, DC},
   isbn = {978-1-64368-252-5},
   pages = {131-137},
   publisher = {IOS Press},
   title = {Human Evaluation Experiment of Legal Information Retrieval Methods},
   url = {https://ebooks.iospress.nl/volume/legal-knowledge-and-information-systems-jurix-2021-the-thirty-fourth-annual-conference-vilnius-lithuania-810-december-2021},
   year = {2021}
}

TY  - CONF
ID  - 1810038
AU  - Novotná, Tereza
PY  - 2021
TI  - Human Evaluation Experiment of Legal Information Retrieval Methods
PB  - IOS Press
CY  - Amsterdam, Berlin, Washington, DC
SN  - 9781643682525
KW  - human evaluation
KW  - court decisions retrieval
KW  - doc2vec
KW  - citation analysis
KW  - LDA
KW  - multilayered approach
UR  - https://ebooks.iospress.nl/volume/legal-knowledge-and-information-systems-jurix-2021-the-thirty-fourth-annual-conference-vilnius-lithuania-810-december-2021
N2  - In this article, I present the results of the human evaluation experiment of three commonly used methods in legal information retrieval and a new ”multilayered” approach. I use the doc2vec model, citation network analysis and two topic modelling algorithms for the Czech Supreme Court decisions retrieval and evaluate their performance. To improve the accuracy of the results of these methods, I combine the methods in a ”multilayered” way and perform the subsequent evaluation. Both evaluation experiments are conducted with a group of legal experts to assess the applicability and usability of the methods for legal information retrieval. The combination of the doc2vec and citations is found satisfactory accurate for practical use for the Czech court decisions retrieval.
ER  -

NOVOTNÁ, Tereza. Human Evaluation Experiment of Legal Information Retrieval Methods. Online. In Erich Schweighofer. \textit{Frontiers in Artificial Intelligence and Applications, Vol. 346 Legal Knowledge and Information Systems. Proceedings of JURIX 2021.}. vol. 346. Amsterdam, Berlin, Washington, DC: IOS Press, 2021, s.~131-137. ISBN~978-1-64368-252-5. Dostupné z: https://doi.org/10.3233/FAIA210328.

Přehled o publikaci