Hukuk Metinleri için Anahtar Kelime Kullanımı ile Otomatik Özetleme

Öz

Mahkemelerde, benzer davalar için önceki mahkemelerin verdiği kararlar mevcut mahkemenin karar verme sürecinde bağlayıcı bir etkiye sahiptir. Bu nedenle avukatlar yer aldıkları davalar ile benzerlik içeren davalara ve sonuçlara ulaşmak için araştırma yaparlar. Hukuki metinlerde aranan duruma ilişkin farklı emsal kararların varlığı, kullanıcının yaptığı aramaya göre birden fazla mahkeme sonuç metninin incelenmesini gerektirir. Metin sayısının fazla olması ve metinlerin yazı miktarlarının büyük olması, kullanıcı tarafından önemli bir zaman ve emek harcanmasına neden olur. Kararlarda özet metinlerin kullanılması, bu süreyi ve çabayı daha makul bir kullanım düzeyine indirecektir. Bu nedenle, bu çalışma, bu yasal metinler için otomatik bir özetleme sistemi geliştirmeyi amaçlamaktadır. Bu amaçla özet çıkarımı ile anahtar kelime frekans temelli özetleme, yönsüz çizge kullanımı ile özet çıkarma, ağırlıklı çizge kullanımı ile özet çıkarımı ve frekans temelli özetleme ile çizge tabanlı özetlemenin hibrit olarak kullanıldığı karma model uygulanmıştır. Bu modellerden en başarılısı karma model olarak belirlenmiştir.

Anahtar Kelimeler

• Doğal dil işleme
• Otomatik özet çıkarımı
• Hukuki metinler

Automatic Summarization with Keyword for Legal Texts

Öz

In legal cases, the decisions made by the previous courts for similar cases affect the determination of current courts. Therefore, lawyers do research to reach similar cases and results. The existence of different precedent decisions regarding the situation sought in the legal texts requires the examination of more than one court result text according to the search made by the user. The high number of texts and the high size of the texts cause a significant time and effort to open by the user. The use of summary texts for decisions will reduce this time and effort to a more reasonable level of use. Therefore, this study aim to develop an automatic summarization system for these legal texts. For this purpose, frequency base, undirected graph base, weighted graph base summarization extraction methods have applied. In addition, a hybrid method that consists frequency base and weighted graph base summarization has applied. This method has best results.

Anahtar Kelimeler

• Natural language processing
• Automatic summarization
• Legal texts

Kaynakça

1. Aseervatham, S., Antoniadis, A., Gaussier, É., Burlet, M., ve Denneulin, Y. (2011). A sparse version of the ridge logistic regression for large-scale text categorization. Pattern Recognition Letters, 32(2), 101-106.
2. Breuker, J., Valente, A., ve Winkels, R. (2004). Legal ontologies in knowledge engineering and information management. Artificial intelligence and law, 12(4), 241-277.
3. Carenini, G., ve Cheung, J. C. K. (2008, June). Extractive vs. NLG-based abstractive summarization of evaluative text: The effect of corpus controversiality. In Proceedings of the Fifth International Natural Language Generation Conference (pp. 33-41).
4. Carenini, G., Cheung, J. C. K., ve Pauls, A. (2013). Multi‐document summarization of evaluative text. Computational Intelligence, 29(4), 545-576.
5. Cortes, C., ve Vapnik, V. (1995). Support-vector networks. Machine learning, 20(3), 273-297.
6. DeJong, G. (1982). An overview of the FRUMP system. Strategies for natural language processing, 113, 149-176.
7. Erkan, G., ve Radev, D. (2004, July). Lexpagerank: Prestige in multi-document text summarization. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (pp. 365-371).
8. Ganesan, K., Zhai, C., ve Han, J. (2010). Opinosis: A graph based approach to abstractive summarization of highly redundant opinions.

9. Gatt, A., ve Reiter, E. (2009, March). SimpleNLG: A realisation engine for practical applications. In Proceedings of the 12th European Workshop on Natural Language Generation (ENLG 2009) (pp. 90-93). Güran, A., Bekar, E., ve Akyokuş, S. (2010). A comparison of feature and semantic-based summarization algorithms for Turkish.
10. Hovy, E., ve Lin, C. Y. (1999). Automated text summarization in SUMMARIST. Advances in automatic text summarization, 14, 81-94.
11. Höfler, S., ve Sugisaki, K. (2012, April). From drafting guideline to error detection: Automating style checking for legislative texts. Association for Computational Linguistics.
12. Ikonomakis, M., Kotsiantis, S., ve Tampakas, V. (2005). Text classification using machine learning techniques. WSEAS transactions on computers, 4(8), 966-974.
13. Joachims, T. (1998, April). Text categorization with support vector machines: Learning with many relevant features. In European conference on machine learning (pp. 137-142). Springer, Berlin, Heidelberg.
14. Lame, G. (2005). Using NLP techniques to identify legal ontology components: concepts and relations. In Law and the Semantic Web (pp. 169-184). Springer, Berlin, Heidelberg.
15. Lehmam, A. (2010). Essential summarizer: innovative automatic text summarization software in twenty languages. In Adaptivity, personalization and fusion of heterogeneous information (pp. 216-217).
16. Lenci, A., Montemagni, S., Pirrelli, V., ve Venturi, G. (2007). NLP-based ontology learning from legal texts. A case study. LOAIT, 321, 113-129.
17. Lenci, A., Montemagni, S., Pirrelli, V., ve Venturi, G. (2009). Ontology learning from Italian legal texts. Law, Ontologies and the Semantic Web, 188, 75-94.
18. Liu, F., Pennell, D., Liu, F., ve Liu, Y. (2009, June). Unsupervised approaches for automatic keyword extraction using meeting transcripts. In Proceedings of human language technologies: The 2009 annual conference of the North American chapter of the association for computational linguistics (pp. 620-628).
19. Turney, P. D. (2000). Learning algorithms for keyphrase extraction. Information retrieval, 2(4), 303-336.
20. Saggion, H., ve Lapalme, G. (2002). Generating indicative-informative summaries with sumum. Computational linguistics, 28(4), 497-526.
21. Uzun, Y. (2005). Keyword extraction using naive bayes. In Bilkent University, Department of Computer Science, Turkey www. cs. bilkent. edu. tr/~ guvenir/courses/CS550/Workshop/Yasin_Uzun. pdf. Yargıtay içtihat. (2021). Erişim Tarihi: 25 Nisan 2021, from https://karararama.yargitay.gov.tr/YargitayBilgiBankasiIstemciWeb/
22. Zhang, H., Fiszman, M., Shin, D., Miller, C. M., Rosemblat, G., ve Rindflesch, T. C. (2011). Degree centrality for semantic abstraction summarization of therapeutic studies. Journal of biomedical informatics, 44(5), 830-838.