NLPDA MATNLARNI UMUMIYLASHTIRISH VA LEKSIK TAHLIL
Keywords:
NLP, Deep learning, lexical analysis, artificial intelligence, summarization, model, vector, matrixAbstract
It is remarkable that there is so much progress in NLP using text summarization, in this article we will use deep learning to create a step-by-step approach to text summarization, covering all the concepts needed for text summarization. We looked at the -step process and implemented our first text summarization model, and for Summarization we looked at inference types and implementation steps and processes.
References
Abduraxmonova N. Mashina tarjimasining lingvistik ta’minoti(monografiya).- Toshkent:Muharrir, 2018. 66-86 b.
Abduraxmonova N. O‘zbek tili elektron korpusining kompyuter modellari(monografiya).- Toshkent:Muharrir, 2021.165 b.
Напр., Krovetz R. (2000). Viewing morphology as an inference process. In Artificial Intelligence, 118, 277–294.
Напр., Sheremetyeva S., Nirenburg S., Nirenburg I. (1996). Generating Patent Claims from Interactive Input. In Proceedings of the 8th International Workshop on Natural Language Generation (Herstmonceux, Sussex, June 1996), 61–70.
Goldsmith, J. (2001). Unsupervised Learning of the Morphology of a Natural Language. In Computational Linguistics, 27(2), 153–198.
Ford A., & Singh R. (1991). Propedeutique Morphologique. Folia Linguistica, 25 (3–4), 549–575; Neuvel Sylvain (2002). Whole Word Morphologizer: Expanding the Word- Based Lexicon: A Nonstochastic Computational Approach. In Brain and Language 81, 454–463.
Neural Machine Translation (seq2seq) Tutorial – Режим доступа: https://www.tensorflow.org/tutorials/seq2seq.
Word2vec – Режим доступа: https://ru.wikipedia.org/wiki/Word2vec.
Klymenko, N. F. et al. (2014). Morfemno-slovotvirnyj fond ukrajins’koji movy jak doslidnyc’ka ta informacijno-dovidkova systema. In Klymenko N. F. Vybrani praci, pages 545–558, Kyiv. 10. Korpus ukrajins’koji movy. Accessible at: http://www.mova.info/corpus.aspx, retrieved 2017-03-15.
