1916

Eski Dilde Kullanılan Sözcükler Arasındaki Anlamsal Yakınlıkların Doğal Dil İşleme Yöntemleriyle Tespiti

Makina öğrenme tekniklerinin doğal dil işleme alanında kullanımı son yıllarda oldukça popüler bir çalışma konusu haline gelmiştir. Doğal dil işleme yöntemlerinin yabancı dillerdeki birçok uygulamasına rastlanılmasına rağmen Türkçe ve özellikle eski dil metinlerdeki uygulamaları oldukça yetersizdir. Bu alandaki eksikliğin giderilmesine yönelik olarak yapılan bu çalışmada, Kültür Bakanlığı kaynaklarından elde edilen 32000 sayfa doküman, temizleme işleminden geçirildikten sonra, bu metinlerden elde edilen kelimeler üzerinde iki katmanlı bir sinir ağı modeli çalıştırılmıştır. Pencere boyutu, uzay boyutu, örnekleme miktarı gibi birçok farklı parametre ile geliştirilen modellere ait vektör uzayları bir sunucuya kopyalanarak bir sorgulama sistemi ve RESTful API servisleri oluşturulmuştur. Ayrıca bu sorgulama sisteminin doğrudan kullanabilmesi için bir kullanıcı portalı oluşturularak RESTful API ile beraber internet kullanımına açılmıştır. Yapılan bu çalışmanın iki farklı amaçla kullanılması hedeflenmektedir. Birinci hedef bu sistemin Türk Dil Kurumu ve Kültür Bakanlığı gibi kurumların ve diğer eski dil sözlük hizmeti sağlayan şirketlerin internet sitelerine entegre edilmesi ve aratılan sözcüklere yakın terimlerin kullanıcılara getirilmesidir. İkinci hedef ise tarih ve edebiyat gibi eski dilin kullanıldığı bilimsel çalışmalarda metinlerin günümüz Türkçe’sine çevrilmesi esnasında ortaya çıkan hataların azaltılmasıdır.

Anahtar Kelimeler:

Doğal dil işleme, Kelime simgeleri, NLP, Yapay sinir ağları

Using NLP Methods For The Discovery Of Semantic Similarities Between Words In Old Turkish Language

Leveraging machine learning techniques in NLP domain has been a very hot research field due to the advancements in artificial intelligence area. Despite the popularity of this field, there is no known study on application of ML techniques on old Turkish language. This study aims to fill in this gap where 32000 pages of text has been downloaded from the websites of Ministry of Culture and a two-layer neural network model has been built on top of them to discover the semantic similarities between Turkish words in old Turkish language. The algorithm has been run with different parameters such as window size, dimension size, sampling size etc. and the produced vector spaces are uploaded into public servers for the purposes of enabling a RESTful API based query interface. Also a web UI has been created to provide a querying mechanism for regular users. The services that are developed can be used for two different purposes. One of them is to integrate these services into existing old Turkish language dictionary websites that are made available by third party providers as well as other institutions such as Ministry of Culture and Turkish Language Institution. Secondly, the developed services are intended to be used for mitigating the translation errors made during the translation of old Turkish texts into modern Turkish language in the areas of history and Turkish literature. Also enabling these services for public use will encourage other researchers to pursue this academic work and compare their results with the experimental results presented in this paper to make further improvements in this field.

Keywords:

Artificial neural networks, Natural language processing, NLP, Word embeddings,

PDF

___

Adıgüzel, H., Şahin, P., Kalpaklı, M., 2012. Line segmentation of Ottoman documents. 20th Signal Processing and Communications Applications Conference, Fethiye Mugla, Turkey.
Arifoğlu, D., Duygulu, P., 2011. Word retrieval in ottoman documents. IEEE 19th Signal Processing and Communications Applications Conference, Antalya, Turkey.
Ataer, E., Duygulu P., 2007. Matching ottoman words: an image retrieval approach to historical document indexing. Proceedings of the 6th ACM international conference on Image and video retrieval, Amsterdam, Netherlands.
Basu, M., Roy, A., Ghosh, K., Bandyopadhyay, S., Ghosh, S., 2017. A Novel Word Embedding Based Stemming Approach for Microblog Retrieval During Disasters. 39th European Conference on Information Retrieval, Scotland, UK.
Can, B., 2017. Unsupervised learning of allomorphs in Turkish. Turkish Journal of Electrical Engineering & Computer Sciences 25(4), 3253-3260.
Chris, B., Faralli, S., Panchenko, A., Ponzetto, S., 2018. A framework for enriching lexical semantic resources with distributional semantics. Natural Language Engineering, Cambridge University Press, 24(1), 265-312.
Church, K. W., 2017. Word2Vec. Natural Language Engineering: Cambridge University Press, 155 p.
Deniz, K., Özçift, A., Bozyigit, F., Yıldırım, P., Yücalar F., Borandag E., 2017. TTC-3600: A new benchmark dataset for Turkish text categorization. Journal of Information Science, 43(2), 174-185.
Ganggao, Z., Iglesias, C. A., 2017. Computing Semantic Similarity of Concepts in Knowledge Graphs. IEEE Transactions on Knowledge and Data Engineering, 29(1), 72-85.
İlgen, B., Adalı, E., Tantuğ, A., 2016. Exploring feature sets for Turkish word sense disambiguation. Turkish Journal of Electrical Engineering & Computer Sciences, 24(1), 4391-4405.
Kalender, M., Korkmaz, E. E., 2018. THINKER - Entity Linking System for Turkish Language. IEEE Transactions on Knowledge and Data Engineering, 30(2), 367-380.
Kaya, Y., Ertugrul, O., 2016. A novel feature extraction approach for text-based language identification: Binary patterns. Journal of the Faculty of Engineering and Architecture of Gazi University, 31(4)
Kılıç, N., Gorgel, P., Ucan N., Kala, A., 2008. Multifont Ottoman character recognition using support vector machine. In Communications, Control and Signal Processing. St Julians, Malta.
Lushan H., Finin, T., McNamee, P., Joshi, A., Yesha, Y., 2013. Improving Word Similarity by Augmenting PMI with Estimates of Word Polysemy. IEEE Transactions on Knowledge and Data Engineering, 25(6), 1307-1322.
Marrero, M, Urbano, J., 2018. A Semi-automatic and low-cost method to learn patterns for named entity recognition. Natural Language Engineering, 24(1), 39-75.
Metin, B., Amasyalı, M., 2017. Dependency parsing with stacked conditional random fields for Turkish. Journal of the Faculty of Engineering and Architecture of Gazi University 32(2).
Mikolov, T., Chen, K., Corrado, G., Dean, J., 2013. Efficient Estimation of Word Representations in Vector Space: arXiv preprint, 1301.3781.
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J., 2013. Distributed Representations of Words and Phrases and Their Compositionality. Proceedings of the 26th International Conference on Neural Information Processing Systems, Lake Tahoe, Nevada.
Ozturk, A., Gunes, S., Ozbay, Y., 2000. Multifont Ottoman character recognition. 7th IEEE International Conference on Electronics, Circuits and Systems, Montreal, Quebec.
Peipei, L., Wang, H., Zhu, K. Q., Wang, Z., Hu, X., Wu, X., 2015. A Large Probabilistic Semantic Network Based Approach to Compute Term Similarity. IEEE Transactions on Knowledge and Data Engineering, 27(1), 2604-2617.
Soon, W. M., Ng, H. T., Lim, D., 2001. A machine learning approach to coreference resolution of noun phrases. Computational linguistics, 27(4), 521-544.
URL-1, 2016. http://ekitap.kulturturizm.gov.tr/TR,78353/divanlar-ve-mesneviler.html
URL-2, 2018. http://snowball.tartarus.org/
URL-3, 2019. https://code.google.com/archive/p/word2vec/source/default/source
URL-4, 2019. http://snowball.tartarus.org/algorithms/turkish/stemmer.html
URL-5, 2019. https://code.google.com/archive/p/word2vec/