Automating the development of semantic models for application programming interfaces

Igor V. Evchenko

Abstract


This article analyzes the problem of automating the creation of semantic models for application programming interfaces, which provides the transformation of user queries in natural language into accurate API method calls. Existing approaches to developing natural language user interfaces are reviewed, including the use of natural language processing techniques, pre-trained language models, and specialized thesauruses. The paper proposes an algorithm for the automated generation of semantic models for application programming interfaces. A test environment was implemented to evaluate the proposed approach, providing dynamic mapping of user queries to API methods. Based on the results, it can be concluded that the proposed method improves the accuracy and completeness of query transformations, minimizes manual intervention, and ensures the model’s adaptability to changes in API structures.

 


Full Text:

PDF (Russian)

References


Tirupati K., Joshi A., Singh C, Akshun J., Shalu G. Leveraging Power BI for Enhanced Data Visualization and Business Intelligence // Universal Research Reports. 2024, P. 676-711.

Poulter. С. Voice recognition software – Nuance Dragon naturally speaking // Occupational Medicine. Volume 70, Issue 1, 2020, P. 75-76.

Su Y., Awadallah A., Khabsa M., Pantel P., Gamon M., Encarnacion M. Building Natural Language Interfaces to Web APIs. // In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management (CIKM '17). Association for Computing Machinery, New York, NY, USA, 2017, P. 177-186.

Hosseini S., Awadallah A., Su Y. Compositional generalization for natural language interfaces to web apis // arXiv, 2021.

Posevkin R.V., Bessmertny I.A. Natural-language user interface of the dialog system // Software Products and Systems. № 3, 2016, С. 5-9.

Devlin J., Chang M.-W., Lee K., Toutanova K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding // Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 2019, P. 4171-4186.

Radford A., Narasimhan K., Salimans T., Sutskever I. Improving language understanding with unsupervised learning: tech. rep., 2018.

Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A., Kaiser L., Polosukhin I. Attention is All you Need // Advances in Neural Information Processing Systems 3. Curran Associates, Inc., 2017, P. 5998-6008.

Bourhis P., Reutter J., Vrgoč D. JSON: Data model and query languages // Information Systems, Volume 89, 2020.

Erofeeva I., Solov'ev V., Bayrasheva V. Psychosemantic experiment as a tool for objectifying data on synonymy (on the material of the Russian language) // Vestnik VolSU. Series 2: Linguistics. 2020.

Kirillovich, A., Nevzorova, O., Gimadiev, E., Loukachevitch, N. RuThes Cloud: Towards a Multilevel Linguistic Linked Open Data Resource for Russian. // Knowledge Engineering and Semantic Web (KESW). Springer, vol 786, 2017.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность IT Congress 2024

ISSN: 2307-8162