Automatic Classification of Semantic Units in Case Law
Vol.11,No.21(2020)
This paper describes a machine learning experiment that showed relatively high- fidelity classification of denotation segments on aminimal dataset using a combination of known machine learning algorithms. By denotation segments we mean segments such as header, proceeding history and party argumentation.
case law; machine learning; natural language processing
s. 3–20
Martin Eliášek
ATLAS Consulting, spol. s r.o.
Jakub Kól
ATLAS Consulting, spol. s r.o.
Miloš Švaňa
ATLAS Consulting, spol. s r.o.
[1] AGGARWAL, Charu C. a ChengXiang ZHAI. Mining text data. New York: Springer, 2012. ISBN 978-1-4614-3222-7. https://doi.org/10.1007/978-1-4614-3223-4_1
[2] HAN, Jiawei, Micheline KAMBER a Jian PEI. Data Mining: Concepts and Techniques. Third Edition. Waltham: Elsevier, 2011. ISBN 978-0-12-381479-1.
[3] HARAŠTA, Jakub, Jaromír ŠAVELKA, František KASL a Jakub MÍŠEK. Automatic Segmentation of Czech Court Decisions into Multi-Paragraph Parts. Jusletter IT. Weblaw AG, 2019, roč. 4, 23. Mai 2019, s. 1-10. ISSN 1664-848X. Dostupné z: https://www.muni.cz/en/research/publications/1534440
[4] MIKOLOV, Tomáš, Kai CHEN, Greg CORRADO a Jefrey DEAN. Efficient Estimation of Word Representations in Vector Space. CoRR, 2013. Dostupné z: https://arxiv.org/abs/1301.3781
[5] MIKOLOV, Tomáš a Quoc V. LE. Distributed Representations of Sentences and Documents. CoRR, 2014. Dostupné z: https://arxiv.org/abs/1405.4053
[6] RASCHKA, Sebastian. Python Machine Learning. Birmingham: Packt, 2015. ISBN 978-1- 78355-513-0.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright © 2020 Martin Eliášek, Jakub Kól, Miloš Švaňa