B.S. Goryachkin1, R.I. Kim2

1,2 Bauman Moscow State Technical University (Moscow, Russia)

1 bsgor@mail.ru, 2 radmir.kim99@yandex.ru

Problem setting. Building a dialog system is a voluminous and complex task that includes many classical tasks of natural language processing. One of the most important tasks is the Named Entity Recognition (NER), since entities are the hard ontologies for determining the meaning of the text. All entities can be divided into 3 groups: "flat" or regular entities, nested entities, and text-separated entities. When solving the NER problem, the difficulty arises with the construction of a universal model for the qualitative processing of all types of entities. In this paper different approaches for the recognition of each type of entities are studied and analyzed, benchmark solutions are identified and the structure of a hybrid model to handle all types of entities is proposed.

Target. Analyzing and comparing the reference solutions for each type of entities. Synthesize different solutions based on the components of the reference models to solve the NER problem with a single model, compare and identify the best models in terms of speed and accuracy.

Results. It was shown that each of the reference models for a particular type of entities does not give high quality in the processing of all types. Based on this, different architectures based on the components of the reference solutions were developed to find a universal model architecture for processing all types of entities. Through comparison and analysis, optimal architectures were identified, both in terms of speed and accuracy, capable of showing high quality performance for all types of entities.

Practical significance. The developed model architectures allow to process all types of entities qualitatively with one universal model.  The resulting models cover all types of entities and surpass the basic solutions in terms of average speed and accuracy.

Goryachkin B.S., Kim R.I. Analysis and synthesis of machine learning models for solving the problem of searching for named entities. Neurocomputers. 2024. V. 26. № 3. Р. 5-13. DOI: https://doi.org/10.18127/j19998554-202403-01 (In Russian)

1. Gapanyuk Yu.E., Leontiev A.V., Latkin I.I., Chernobrovkin S.V., Belyanova M.A., Morozenkov O.N. Hybrid intelligent Russian-language dialog information system based on a metagraphic approach. Dynamics of complex systems – XXI century. 2018. V. 12. № 1.
   P. 77–86. (In Russian)
2. Monakhov Yu.M., Artyushina L.A., Makov E.O., Ismailova M.R. Model of an intelligent dialog system for automated ticket ordering based on semantic analysis. Dynamics of complex systems – XXI century. 2018. V. 12. № 2. P. 75–80. (In Russian)
3. Tarassov V.B., Gapanyuk Yu.E. Complex Graphs in the Modeling of Multiagent Systems: From Goal-Resource Networks to Fuzzy Metagraphs. Lecture notes in computer science. 2020. V. 12412. P. 177–198. DOI 10.1007/978-3-030-59535-7_13.
4. Belyanova M.A., Andreev A.M., Gapanyuk Yu.E. Neural Text Question Generation for Russian Language Using Hybrid Intelligent Information Systems Approach. Studies in Computational Intelligence. 2022. V. 1008 SCI. P. 217–223. DOI 10.1007/978-3-030-91581-0_29.
5. Wang J., Shou L., Chen K., Chen G. Pyramid: A Layered Model for Nested Named Entity Recognition. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020. P. 5918–5928. DOI 10.18653/v1/2020.acl-main.525.
6. Wang Y., Yu B., Zhu H., Liu T., Yu N., Sun L. Discontinuous Named Entity Recognition as Maximal Clique Discovery. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. 2021. V. 1 Long Papers. P. 764–774. DOI 10.18653/v1/2021.acl-long.63.
7. Dong L., Yang N., Wang W., Wei F., Liu X., Wang Y., Gao J., Zhou M., Hon H.-W. Unified Language Model Pre-training for Natural Language Understanding and Generation. Neural Information Processing Systems. 2019. DOI 10.48550/arXiv.1905.03197.
8. Yu J., Bohnet B., Poesio M. Named Entity Recognition as Dependency Parsing. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020. P. 6470–6476. DOI 10.18653/v1/2020.acl-main.577.
9. Luo L., Lai P.-T., Wei C.-H., Arighi C.N., Lu Z. BioRED: A Rich Biomedical Relation Extraction Dataset. Briefings in Bioinformatics. 2022. V. 23. № 5. DOI 10.1093/bib/bbac282.
10. Le T.A., Arkhipov M.Y., Burtsev M.S. Application of a hybrid BI-LSTM-CRF model to the task of Russian named entity recognition. Communications in computer and information science. 2017. V. 789. P. 91–103. DOI 10.1007/978-3-319-71746-3_8.