國立虎尾科技大學 |

Prediction of Outcomes in Higher Courts of Turkey Using Natural Language Processing = = Dogal Dil Isleme Yontemleri Kullanilarak Turk Yuksek Mahkemelerinde Karar Tahmini.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Prediction of Outcomes in Higher Courts of Turkey Using Natural Language Processing =/
Reminder of title:	Dogal Dil Isleme Yontemleri Kullanilarak Turk Yuksek Mahkemelerinde Karar Tahmini.
remainder title:	Dogal Dil Isleme Yontemleri Kullanilarak Turk Yuksek Mahkemelerinde Karar Tahmini.
Author:	Mumcuoglu, Emre.
Description:	1 online resource (71 pages)
Notes:	Source: Masters Abstracts International, Volume: 84-02.
Contained By:	Masters Abstracts International84-02.
Subject:	Language. -
Online resource:	click for full text (PQDT)
ISBN:	9798841571407

Prediction of Outcomes in Higher Courts of Turkey Using Natural Language Processing = = Dogal Dil Isleme Yontemleri Kullanilarak Turk Yuksek Mahkemelerinde Karar Tahmini.
Mumcuoglu, Emre.

Prediction of Outcomes in Higher Courts of Turkey Using Natural Language Processing =Dogal Dil Isleme Yontemleri Kullanilarak Turk Yuksek Mahkemelerinde Karar Tahmini.Dogal Dil Isleme Yontemleri Kullanilarak Turk Yuksek Mahkemelerinde Karar Tahmini. - 1 online resource (71 pages)

Source: Masters Abstracts International, Volume: 84-02.

Thesis (M.Sc.)--Bilkent Universitesi (Turkey), 2022.

Includes bibliographical references

The use of Natural Language Processing (NLP) in the field of law has become a topic of interest in the recent years. Applications to Turkish law, however, have remained unexplored to this day. In this thesis, first, a review of existing NLP applications in law is provided, and then, the problem of predicting Turkish court decisions is studied using NLP techniques. An extensive corpus that consists of case texts from Turkish higher courts, namely, the Constitutional Court and District Courts, is compiled. In addition, a numerical analysis and comparison of NLP methods at predicting the outcomes of these higher court cases is provided. The methods used for prediction are based on Decision Trees, Random Forests, Support Vector Machines and various deep learning models; specifically Gated Recurrent Units, unidirectional and bidirectional Long Short-Term Memory networks, and their attention-integrated counterparts. Prediction results for all algorithms are presented comparatively across all courts. The results show that decisions of Turkish higher courts can be predicted with high accuracy, especially with deep learning-based methods. Similar performance to existing work in the literature on case outcome prediction, which focus on different languages and different legal systems, is achieved.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798841571407Subjects--Topical Terms:

571568
Language.
Index Terms--Genre/Form:

554714
Electronic books.

Prediction of Outcomes in Higher Courts of Turkey Using Natural Language Processing = = Dogal Dil Isleme Yontemleri Kullanilarak Turk Yuksek Mahkemelerinde Karar Tahmini.
LDR:04323ntm a2200409K 4500 001 1141199
005 20240116054223.5
006 m o d
007 cr mn ---uuuuu
008 250605s2022 xx obm 000 0 eng d
020 $a 9798841571407
035 $a (MiAaPQ)AAI29274669
035 $a (MiAaPQ)Bilkent_1169379425
035 $a AAI29274669
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Mumcuoglu, Emre. $3 1464848
245 1 0 $a Prediction of Outcomes in Higher Courts of Turkey Using Natural Language Processing = $b Dogal Dil Isleme Yontemleri Kullanilarak Turk Yuksek Mahkemelerinde Karar Tahmini.
246 3 1 $a Dogal Dil Isleme Yontemleri Kullanilarak Turk Yuksek Mahkemelerinde Karar Tahmini.
264 0 $c 2022
300 $a 1 online resource (71 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 84-02.
500 $a Advisor: Ozaktas, Memduh Haldun ; Koc, Aykut ; Cukur, Tolga ; Turkmen, Arzucan Ozgur.
502 $a Thesis (M.Sc.)--Bilkent Universitesi (Turkey), 2022.
504 $a Includes bibliographical references
520 $a The use of Natural Language Processing (NLP) in the field of law has become a topic of interest in the recent years. Applications to Turkish law, however, have remained unexplored to this day. In this thesis, first, a review of existing NLP applications in law is provided, and then, the problem of predicting Turkish court decisions is studied using NLP techniques. An extensive corpus that consists of case texts from Turkish higher courts, namely, the Constitutional Court and District Courts, is compiled. In addition, a numerical analysis and comparison of NLP methods at predicting the outcomes of these higher court cases is provided. The methods used for prediction are based on Decision Trees, Random Forests, Support Vector Machines and various deep learning models; specifically Gated Recurrent Units, unidirectional and bidirectional Long Short-Term Memory networks, and their attention-integrated counterparts. Prediction results for all algorithms are presented comparatively across all courts. The results show that decisions of Turkish higher courts can be predicted with high accuracy, especially with deep learning-based methods. Similar performance to existing work in the literature on case outcome prediction, which focus on different languages and different legal systems, is achieved.
520 $a Dogal Dil Isleme'nin (DDI) hukuk alanindaki uygulamalari arastirmacilarin son yillarda artarak ilgisini cekerken Turk hukuku icin olasi uygulamalari inceleyen bir calisma bulunmamaktadir. Biz, ilk olarak DDI'nin halihazirda literaturde olan hukuki uygulamalarini gozden geciriyor, sonra da Turk mahkemeleri ozelinde dava metinlerinden mahkeme kararini tahmin etme problemini ele aliyoruz. Bu tezin alana baslica iki katkisindan ilki, Turk yuksek mahkemelerinden Anayasa Mahkemesi ve Istinaf Mahkemelerinin karar metinlerinden kapsamli bir der- lem olusturulmasidir. Ikinci katkisi ise, bu dava metinleri uzerinden mahke- menin kararini tahmin etmede cesitli DDI yontemlerinin nicel olarak incelen- mesi ve kiyaslanmasidir. Karar tahmin etmede kullanilan algoritmalar Karar Agaclari, Rastgele Ormanlar, Destek Vektoru Makineleri ve muhtelif derin ogrenme yontemlerine dayanmaktadir. Sozu gecen derin ogrenme yontemleri Gecitli Mukerrer Hucreler, tek yonlu ve cift yonlu Uzun-Kisa Vade Hafiza aglari ve bunlarin dikkat mekanizmasi eklenmis cesitleridir. Butun bu algoritmalarin karar tahminindeki performanslarmi her bir mahkeme icin mukayeseli bir bicimde ortaya koyuyoruz. Turk yuksek mahkemelerinin kararlarinin ozellikle derin ogrenme yontemleri kullanilarak yuksek isabet oranlariyla tahmin edilebilecegini gosteriyoruz. Diger ulkelerin mahkemeleri icin farkli dillerdeki dava metinlerinde yapilmis benzer calismalara yakin sonuclar elde ediyoruz.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Language. $3 571568
650 4 $a Text categorization. $3 1464781
650 4 $a Deep learning. $3 1127428
650 4 $a Judiciary. $3 1464849
650 4 $a Legal documents. $3 1464850
650 4 $a District courts. $3 1464851
650 4 $a Constitutional law. $3 564349
650 4 $a Support vector machines. $3 641425
650 4 $a Jurisdiction. $3 559835
650 4 $a Legislation. $3 803490
650 4 $a Natural language processing. $3 1050360
650 4 $a Algorithms. $3 527865
650 4 $a Decision trees. $3 670945
650 4 $a Federal court decisions. $3 1464852
650 4 $a Human rights. $3 554782
650 4 $a Information retrieval. $3 563691
650 4 $a Judges & magistrates. $3 1464853
650 4 $a Computer science. $3 573171
650 4 $a Law. $3 671705
650 4 $a Middle Eastern studies. $3 1179422
650 4 $a Political science. $3 558774
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0679
690 $a 0984
690 $a 0398
690 $a 0555
690 $a 0615
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Bilkent Universitesi (Turkey). $3 1413631
773 0 $t Masters Abstracts International $g 84-02.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29274669 $z click for full text (PQDT)