Methods for Developing Semantically Oriented Virtual Assistants
https://doi.org/10.25205/1818-7900-2023-21-3-46-55
Abstract
Nowadays, various technologies are used to create intelligent assistants, based both on research in the field of neural networks, natural language text analysis tools, and on the use of semantic modeling tools. Each of these approaches allows you to qualitatively solve certain problems. As part of this work, an intelligent assistant is being developed that combines all these approaches. The purpose of the work is to create an intelligent assistant that performs as a virtual consultant on the organization’s work processes. The development is based on the use of the semantic model of the organization and business processes. To recognize user intents, we use homomorphic and generalized user intents. The system allows decomposing user tasks and creating a consistency of their execution based on the user semantic models and the subject area.
About the Authors
A. S. Tregubov
Novosibirsk State University
Russian Federation
Russian Federation
Artem S. Tregubov, Graduate Studen
Novosibirsk
I. S. Nemtsev
Novosibirsk State University
Russian Federation
Russian Federation
Ivan S. Nemtsev, Master’s Studen
Novosibirsk
A. А. Kotelnikova
Novosibirsk State University
Russian Federation
Russian Federation
Anna A. Kotelnikova, Bachelor
Novosibirsk
D. A. Domozhakova
Novosibirsk State University
Russian Federation
Russian Federation
Darya A. Domozhakova, Bachelor
Novosibirsk
References
1. Chollet, F. Deep learning with Python. St. Petersburg: Piter, 2018, pp. 346–348.
2. Kuratov Y., Arkhipov M. Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language. 2019. arXiv preprint arXiv:1905.07213.
3. Hamilton W. L., Rex Ying, and Leskovec J. Representation learning on graphs: Methods and application // IEEE Data Eng. Bull., 2017a.
4. Sahisnu Mazumder, Nianzu Ma, and Bing Liu. Towards a Continuous Knowledge Learning Engine for Chatbots. 2018. arXiv:1802.06024.
5. Zhanming Jie, Wei Lu. Dependency-guided lstm-crf for named entity recognition // Proceedings of EMNLP. 2019.
6. Kipf Th. N., Welling M. Semi-supervised classification with graph convolutional networks // Proceedings of ICLR. 2017.
7. Gubichev A., Bedathur S., Seufert S., Weikum G. Fast and accurate estimation of shortest paths in large graphs // Proceedings of the 19th ACM International Conference on Information and Knowledge Management, CIKM ’10. New York, NY, USA, 2010. P. 499–508.
8. Fellbaum C. (to appear) Future Challenges for the Princeton WordNet. In: Special Issue on Linking, Integrating and Extending Wordnets. Linguistic Issues in LanguageTechnology, eds. Francis Bond, Christiane Fellbaum and Ewa Rudnicka.
9. Chollet, F. Deep learning with Python. St. Petersburg: Piter, 2018, pp. 173–191.
10. Guo Z., Zhang Y., Lu W. Attention Guided Graph Convolutional Networks for Relation Extraction // Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, 28 July – 2 August 2019. P. 241–251.
11. BERT large model (uncased) for Sentence Embeddings in Russian language. URL: https:// huggingface.co/sberbank-ai/sbert_large_nlu_ru
12. Corso G., Cavalleri L., Beaini D., Lio P., Velicˇkovic ́ P. Principal neighborhood aggregation for graph nets // Advances in Neural Information Processing Systems. 2020. Vol. 33. P. 13260– 13271.
Review
For citations:
Tregubov A.S., Nemtsev I.S., Kotelnikova A.А., Domozhakova D.A. Methods for Developing Semantically Oriented Virtual Assistants. Vestnik NSU. Series: Information Technologies. 2023;21(3):46-55. (In Russ.) https://doi.org/10.25205/1818-7900-2023-21-3-46-55
Views:
185
Email this article 