Araştırma Makalesi
BibTex RIS Kaynak Göster

Çevirmen-Bilgisayar Etkileşiminin Kilit Bileşeni: Doğal Dil İşleme

Yıl 2023, Cilt: 5 Sayı: 1, 56 - 79, 21.06.2023
https://doi.org/10.55036/ufced.1306746

Öz

Yapay zekânın bir alt alanı olan doğal dil işleme, özellikle son yıllarda gündelik yaşamı etkileyen birçok ürünün ortaya çıkmasını sağlamıştır. İnsan dilini öğrenerek makinenin insanla etkili bir şekilde iletişime geçmesini sağlamak üzere geliştirilen doğal dil işleme teknikleri, yalnızca dilbilimde değil, çeviribilim alanında da paradigma değişikliklerine neden olmuştur. Makine çevirisi sistemleri, otomatik özetleme araçları, terim yönetim sistemleri, metin düzenleme ve düzeltme uygulamaları gibi çeviriye yardımcı araçlar, doğal dil işleme teknikleriyle tasarlanmıştır. Söz konusu araçlar, yapay zekâ alanındaki gelişmelerle paralel olarak sürekli güncellenmekte ve kullanıcı beklentilerine göre iyileştirilmektedir. Doğal dil işlemenin en temel çalışma alanlarından biri makine çevirisidir. Doğal dil işleme tabanlı dil modelleri, çeviri kalitesinin artırılması için sürekli olarak eğitilmekte; bağlama dayalı bilginin sistem işleyişine eklemlenmesiyle daha başarılı sonuçlar elde edebilmektedir. Bu çalışmanın amacı, doğal dil işleme araçları ve tekniklerinin günümüz çeviri sürecindeki konumunu tartışmaktır. Bu doğrultuda, öncelikle doğal dil işleme kavramından söz edilecek ve doğal dil işleme uygulamalarının çeviri etkinliğini nasıl etkilediği üzerinde durulacaktır. Ardından başta makine çevirisi teknolojileri olmak üzere çevirmenler tarafından kullanılan doğal dil işleme tabanlı uygulamalar, çeviri odaklı bir bakış açısıyla incelenmeye çalışılacaktır.

Kaynakça

  • All Languages Ltd. Translators & Interpreters. (2016). Machine translation basics. https://www.alllanguages.com/documents/AllLanguagesMachineTranslation.pdf
  • Anderson, A. (2014). Media, environment and the network society. Londra: Palgrave Macmillan. Bowker, L. (2022). Machine translation literacy. https://sites.google.com/view/machinetranslationliteracy/
  • Bowker, L. ve McBride, C. (2017). Précis-writing as a form of speed training for translation students. The Interpreter and Translator Trainer, 11(4), 259-279.
  • Castells, M. (2004). Informationalism, networks, and the network society: A theoretical blueprint. Manuel Castells (Ed.), The network society: A cross-cultural perspective içinde (ss. 3-45). Cheltenham: Edward Elgar.
  • Chesterman, A. (2016). Memes of Translation: The spread of ideas in translation theory, Amsterdam / Philadelphia: John Benjamins Publishing Company.
  • Eisenstein, J. (2018). Natural language processing. MIT Press.
  • Fantinuoli, C. (2023). EasyAI - Introducing artificial intelligence to the humanities. https://easyai.unimainz.de/html/index.html
  • Hettige, B. ve Karunananda, A. S. (2011). Computational model of grammar for English to Sinhala machine translation. International Conference on Advances in ICT for Emerging Regions (ICTer) içinde IEEE, 26-31.
  • Intento (2021). Independent multi-domain evaluation of machine translation engines. https://try.inten.to/machine-translation-report-2021/
  • Johnson, M., Schuster, M., Le, Q. V., Krikun, M., Wu, Y., Chen, Z., Thorat, N., Viégas, F., Wattenberg, M., Corrado, G., Hughes, M., ve Dean, J. (2017). Google’s multilingual neural machine translation system: Enabling zero-shot translation. Transactions of the Association for Computational Linguistics, 5, 339-351.
  • Joseph, S. R., Hlomani, H., Letsholo, K., Kaniwa, F. ve Sedimo, K. (2016). Natural language processing: A review. International Journal of Research in Engineering and Applied Sciences, 6(3), 207-210.
  • Khurana, D., Koli, A., Khatter, K. ve Singh, S. (2022). Natural language processing: State of the art, current trends and challenges. Multimedia Tools and Applications, 82, 3713–3744.
  • Koehn P. (2005). Europarl: A parallel corpus for statistical machine translation. Proceedings of the MT Summit içinde, 5, 79–86.
  • Lakew, S. M., Federico, M., Negri, M. ve Turchi, M. (2018). Multilingual neural machine translation for low-resource languages. IJCoL. Italian Journal of Computational Linguistics, 4(4-1), 11-25.
  • Language Connections (2022). How interpreting services have changed at the olympics. https://www.languageconnections.com/blog/blog-how-interpreting-services-have-changed-atthe-olympics/
  • Ma, Y. ve Tang, J. (2021). Deep learning on graphs. Birleşik Krallık: Cambridge University Press.
  • Madill, W. (2022). Exploring natural language processing (NLP) in translation. https://localizejs.com/articles/natural-language-processing-nlp/
  • Manning, C. ve Schutze, H. (1999). Foundations of statistical natural language processing. Massachusetts: MIT press.
  • Millward, C. M. ve Hayes, M. (2012). A biography of the English language (3. Baskı). Amerika Birleşik Devletleri: Cengage learning.
  • Ping, K. (2011). Machine translation. Mona Baker ve Gabriela Saldanha (Ed.), Routledge encyclopedia of Translation Studies (2. Baskı) içinde (ss. 162-169). Londra ve New York: Routledge.
  • Randhawa, G., Ferreyra, M., Ahmed, R., Ezzat, O. ve Pottie, K. (2013). Using machine translation in clinical practice. Canadian Family Physician, 59(4), 382-383.
  • Rothman, D. (2021). Transformers for natural language processing: Build innovative deep neural network architectures for NLP with Python, PyTorch, TensorFlow, BERT, RoBERTa, and more. Birmingham: Packt Publishing Ltd.
  • Scott, M. L. (2015). Programming language pragmatics. New York: Morgan Kaufmann.
  • Searle, J. R. (1980). Minds, brains and programs. Behavioral and Brain Sciences, 3, 417 – 457.
  • Shreve, G. M. (2006). Integration of translation and summarization processes in summary translation. Translation and Interpreting Studies. The Journal of the American Translation and Interpreting Studies Association, 1(1), 87-109.
  • Stenlund, S. (1990). Language and philosophical problems (1. baskı). Londra ve New York: Routledge.
  • Vandermeulen, B. (2020). Précis translation: Experiences, approaches and performance of third-year students of the bachelor in Applied Linguistics. Universiteit Antwerpen: Lisans Tezi.

The Key Element of Translator-Computer Interaction: Natural Language Processing

Yıl 2023, Cilt: 5 Sayı: 1, 56 - 79, 21.06.2023
https://doi.org/10.55036/ufced.1306746

Öz

Natural language processing (NLP), a subfield of artificial intelligence, has led to the development of many products that affect everyday life, especially in recent years. Developed to learn human language, NLP techniques that enable machines to communicate effectively with humans have led to a paradigm shift not only in linguistics, but also in translation studies. Translation aids such as machine translation systems, automatic summarization tools, terminology management systems, and text review and proofreading applications have been designed with NLP techniques. These tools are continuously updated and improved in parallel with user expectations and the developments in the field of artificial intelligence. One of the most fundamental areas of NLP is machine translation. NLP-based language models are continuously trained in order to improve translation quality, and more successful results can be achieved by incorporating contextual information into the system functioning. The aim of this study is to discuss the role of NLP tools and techniques in translating process. To this end, firstly, the concept of NLP will be discussed and how NLP-based applications affect translation activity will be emphasized. Then, NLP-based applications used by translators, especially machine translation technologies, will be analyzed from a translation-oriented perspective.

Kaynakça

  • All Languages Ltd. Translators & Interpreters. (2016). Machine translation basics. https://www.alllanguages.com/documents/AllLanguagesMachineTranslation.pdf
  • Anderson, A. (2014). Media, environment and the network society. Londra: Palgrave Macmillan. Bowker, L. (2022). Machine translation literacy. https://sites.google.com/view/machinetranslationliteracy/
  • Bowker, L. ve McBride, C. (2017). Précis-writing as a form of speed training for translation students. The Interpreter and Translator Trainer, 11(4), 259-279.
  • Castells, M. (2004). Informationalism, networks, and the network society: A theoretical blueprint. Manuel Castells (Ed.), The network society: A cross-cultural perspective içinde (ss. 3-45). Cheltenham: Edward Elgar.
  • Chesterman, A. (2016). Memes of Translation: The spread of ideas in translation theory, Amsterdam / Philadelphia: John Benjamins Publishing Company.
  • Eisenstein, J. (2018). Natural language processing. MIT Press.
  • Fantinuoli, C. (2023). EasyAI - Introducing artificial intelligence to the humanities. https://easyai.unimainz.de/html/index.html
  • Hettige, B. ve Karunananda, A. S. (2011). Computational model of grammar for English to Sinhala machine translation. International Conference on Advances in ICT for Emerging Regions (ICTer) içinde IEEE, 26-31.
  • Intento (2021). Independent multi-domain evaluation of machine translation engines. https://try.inten.to/machine-translation-report-2021/
  • Johnson, M., Schuster, M., Le, Q. V., Krikun, M., Wu, Y., Chen, Z., Thorat, N., Viégas, F., Wattenberg, M., Corrado, G., Hughes, M., ve Dean, J. (2017). Google’s multilingual neural machine translation system: Enabling zero-shot translation. Transactions of the Association for Computational Linguistics, 5, 339-351.
  • Joseph, S. R., Hlomani, H., Letsholo, K., Kaniwa, F. ve Sedimo, K. (2016). Natural language processing: A review. International Journal of Research in Engineering and Applied Sciences, 6(3), 207-210.
  • Khurana, D., Koli, A., Khatter, K. ve Singh, S. (2022). Natural language processing: State of the art, current trends and challenges. Multimedia Tools and Applications, 82, 3713–3744.
  • Koehn P. (2005). Europarl: A parallel corpus for statistical machine translation. Proceedings of the MT Summit içinde, 5, 79–86.
  • Lakew, S. M., Federico, M., Negri, M. ve Turchi, M. (2018). Multilingual neural machine translation for low-resource languages. IJCoL. Italian Journal of Computational Linguistics, 4(4-1), 11-25.
  • Language Connections (2022). How interpreting services have changed at the olympics. https://www.languageconnections.com/blog/blog-how-interpreting-services-have-changed-atthe-olympics/
  • Ma, Y. ve Tang, J. (2021). Deep learning on graphs. Birleşik Krallık: Cambridge University Press.
  • Madill, W. (2022). Exploring natural language processing (NLP) in translation. https://localizejs.com/articles/natural-language-processing-nlp/
  • Manning, C. ve Schutze, H. (1999). Foundations of statistical natural language processing. Massachusetts: MIT press.
  • Millward, C. M. ve Hayes, M. (2012). A biography of the English language (3. Baskı). Amerika Birleşik Devletleri: Cengage learning.
  • Ping, K. (2011). Machine translation. Mona Baker ve Gabriela Saldanha (Ed.), Routledge encyclopedia of Translation Studies (2. Baskı) içinde (ss. 162-169). Londra ve New York: Routledge.
  • Randhawa, G., Ferreyra, M., Ahmed, R., Ezzat, O. ve Pottie, K. (2013). Using machine translation in clinical practice. Canadian Family Physician, 59(4), 382-383.
  • Rothman, D. (2021). Transformers for natural language processing: Build innovative deep neural network architectures for NLP with Python, PyTorch, TensorFlow, BERT, RoBERTa, and more. Birmingham: Packt Publishing Ltd.
  • Scott, M. L. (2015). Programming language pragmatics. New York: Morgan Kaufmann.
  • Searle, J. R. (1980). Minds, brains and programs. Behavioral and Brain Sciences, 3, 417 – 457.
  • Shreve, G. M. (2006). Integration of translation and summarization processes in summary translation. Translation and Interpreting Studies. The Journal of the American Translation and Interpreting Studies Association, 1(1), 87-109.
  • Stenlund, S. (1990). Language and philosophical problems (1. baskı). Londra ve New York: Routledge.
  • Vandermeulen, B. (2020). Précis translation: Experiences, approaches and performance of third-year students of the bachelor in Applied Linguistics. Universiteit Antwerpen: Lisans Tezi.
Toplam 27 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Dil Çalışmaları
Bölüm Araştırma Makaleleri
Yazarlar

Sevda Pekcoşkun Güner 0000-0003-2750-3217

Yayımlanma Tarihi 21 Haziran 2023
Gönderilme Tarihi 29 Mayıs 2023
Kabul Tarihi 14 Haziran 2023
Yayımlandığı Sayı Yıl 2023 Cilt: 5 Sayı: 1

Kaynak Göster

APA Pekcoşkun Güner, S. (2023). Çevirmen-Bilgisayar Etkileşiminin Kilit Bileşeni: Doğal Dil İşleme. Karamanoğlu Mehmetbey Üniversitesi Uluslararası Filoloji Ve Çeviribilim Dergisi, 5(1), 56-79. https://doi.org/10.55036/ufced.1306746

422x119





422x119

ResearchBib   google akademik ile ilgili görsel sonucu     logo1.jpg     Root Indexing     general impact factor ile ilgili görsel sonucu    idealonline ile ilgili görsel sonucu

220px-Akademia_sosyal_bilimler_indeksi_logosu.gif    DRJI_Logo.jpg    logo.jpg   logo.png      download


by-nc-nd.png?w=588

  Articles published in this journal are licensed under Creative Commons Attribution 4.0 International license. This journal does not charge APCs or submission charges.                                                                           Articles published in this journal are permanently free for everyone to read, download, copy, distribute, print, search and link to the full texts of these articles.