On Text Understanding Modeling by Means of Artificial Intelligence Systems

Purpose of reseach is to conduct a comparative analysis of texts generated by an artificial intelligence system in the process of processing source text in natural language and counter texts that are the result of human understanding of the source literary text. 

Methods. To achieve the goal and objectives of the study, the author used an experimental technique to conduct a comparative analysis of the denotational structures of counter texts. Participants in the experiment (7 4th year students of the Faculty of Additional Education “Translator in the field of professional communications”, 3 associate professors of the Department of Foreign Languages of South- West State University) assessed the success of recreating the semantic structure of the text of 10 counter texts of different nature - generated by AI and humans. 

Results. The results of the experiment indicate that the completeness of the semantic content of the generated text does not depend on the structure of the source text. Modern methods of semantic text processing by an AI system make it possible to obtain the output of full-fledged text works created taking into account the rules and norms of natural language.

AI systems successfully recreate the denotational structure of the text and reconstruct the syntactic structure. 

Conclusion. Access to large databases allows you to train a neural network on large text corpora, which results in an increase in the accuracy and variability of the lexical units and constructs used. The accuracy of conveying the semantic content of the text varies. It depends on the degree of text compression - the higher it is, the less accuracy can be, because the neural network is unable to classify denotational connections for relevance to the underlying meaning. The degree of accuracy in conveying semantic content is determined by the success / failure of understanding the deep hidden meaning, which is determined by the understanding of the linguistic and extralinguistic context. The ability to recognize the situation model recreated in the source text is the key to understanding the hidden meaning. The AI system can recreate the surface denotational structure of the text quite correctly and accurately, but is not able to construct a model of the situation at this stage of development.

1. Gorbachevskaya E.N., Krasnov S.S. Istoriya razvitiya nejronnyh setej [History of Neural Networks Development] [Elektronnyj resurs]. Available at: http://cyberleninka.ru/article/n/istoriya-razvitiya-neyronnyh-setey.

2. Mikolov T. et. al. Efficient Estimation of Word Representations in Vector Space, arxiv.org. URL: http://arxiv.org/pdf/1301.3781.pdf (data obrashcheniya: 24.01.2024).

3. Bobyr' M. V. Obuchenie nejro-nechetkih sistem [Training of Neuro-Fuzzy Systems]. Moscow, ARGAMAK-MEDIA, 2017. 240 p.

4. Velihov P.E. Mashinnoe obuchenie dlya ponimaniya estestvennogo yazyka [Machine Learning for Natural Language Understanding]. Otkrytye Sistemy.SUBD, 2016, no. 1, pp.18– 21. Available at: https://www.osp.ru/os/2016/01/13048649.

5. Anan'ev B.G. Psihologiya chuvstvennogo poznaniya [Psychology of sensual cognition]. Moscow, 1960. 486 p.

6. Blonskij P.P. Pamyat' i myshlenie [Memory and cognition]. Moscow, URSS: LENAND Publ., 2017. 204 p.

7. Borodaj S. Yu. Yazyk i poznanie: Vvedenie v postrelyativizm [Language and cognition: Introduction to postrelativism]. Moscow, 2019. 800 p.

8. Vygotskij L. S. Myshlenie i rech' [Cognition and speech]. Saint Petersburg: Piter Publ., 2019. 431 p.

9. Zalevskaya A.A. Vvedenie v psiholingvistiku [Introduction to Psycholinguistics]. Moscow, RGGU Publ., 2007. 559 p.

10. Sokolov A. N. Vnutrennyaya rech' i myshlenie [Inner speech and cognition]. Moscow, URSS Publ., 2007. 248 p.

11. Myagkova E.YU. Navyk chteniya i problemy ponimaniya teksta [Reading skill and text understanding]. Yazykovoe bytie cheloveka i etnosa. Vyp. 20. Materialy XV Berezinskih chtenij. = The linguistic existence of a person and an ethnic group. Issue 20. Materials of the XV Berezinsky readings. Moscow, INION RAN Publ., 2018, pp. 83–95.

12. Myagkova E. Yu. Yazyk - emocii - soznanie - kul'tura v teorii A. Damasio [Language-emotion-recognition-culture in the theory of A. Damasio]. Voprosy psiholingvistiki=Questions of Psycholinguistics, 2022, no. 4(54), pp. 72-85. DOI 10.30982/2077-59112022-54-4-72-85.

13. Kruzhilina T.V. Ponimanie teksta v ontogeneze [Text Understanding in Ontogenesis]. Kursk, Yugo-Zapadnyj gosudarstvennyj universitet Publ., 2016. 152 p.

14. Kruzhilina T. V. Faktory, opredelyayushchie osobennosti rechevogo razvitiya u detej [Factors that Determine the Characteristics of Speech Development in Children]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta = Proceedings of the Southwest State University, 2012, no. 4–1(43), pp. 216–219.

15. Belyanin V.P. Psiholingvistika [Psycholinguistics]. Moscow, Flinta Publ., 2013. 416 p.

16. Manning Ch. Computational linguistics and deep learning. Computational Linguistics, 2016. Available at: http://www.mitpressjournals.org/doi/full/10.1162/COLI_a_00239#.WQH8MBhh2qA

17. Ish-Kishor S. Svidanie s lyubov'yu [Appointment with Love]. Available at: http://sacralis.com/biblioteka/proza/2605-svidanie_s_lubovju.html?ysclid=ls0tcuhl7u170031708

18. Novikov N.A. Semantika teksta i ee formalizaciya [Text Semantics and its Formalization]. Moscow, Nauka Publ., 1983. 215 p.

19. ZHinkin N.I. O kodovyh perekhodah vo vnutrennej rechi [About code transitions in internal speech]. Moscow, Kul'tura Publ., Akad. Proekt, 2006, pp. 251– 263.

20. Zvyaginceva V.V. Obrashchenie v anglijskom semejnom diskurse (eksperimental'noe issledovanie) [Address in English family discourse (experimental study)]. Izvestiya YugoZapadnogo gosudarstvennogo universiteta. Seriya: Lingvistika i pedagogika = Proceedings of the Southwest State University. Series: Linguistics and Pedagogics, 2012, no. 2, pp. 48–51.