Electrotechnical and Computer Engineering
Vol. 39 No. 11 (2024): Proceedings of Faculty of Technical Sciences
USABILITY OF GRAPHQL LIBRARY FOR DEVELOPMENT OF NLP INTERFACES
Abstract
Conceptual solution of a system that allows users to access data from the warehouse using natular langauge queries. Through the NLP intreface, users make queries in natural language in order to get the desired data. The system automatically translates natural language queries into GraphQL queries that cover the entire API system, including the data warehouse.
References
[1] https://www.ibm.com/topics/natural-language-processing (pristupljeno u junu 2024.)
[2] https://graphql.org (pristupljeno u junu 2024.)
[3] https://www.datacamp.com/blog/what-is-tokenization (pristupljeno u junu 2024.)
[4] https://intellipaat.com/blog/what-is-parsing-in-nlp/ (pristupljeno u junu 2024.)
[5] https://www.geeksforgeeks.org/named-entity-recognition/ (pristupljeno u junu 2024.)
[6] https://www.geeksforgeeks.org/what-is-sentiment-analysis/ (pristupljeno u junu 2024.)
[7] https://ethglobal.com/showcase/the-graph-ai-z9cgp (pristupljeno u junu 2024.)
[8] M. Lewis, Y. Liu, N. Goyal, M. Ghazvininejad, A. Mohamed, O. Levy, V. Stoyanov, L. Zettlemoyer, “BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension”, 2019
[9] https://www.projectpro.io/article/transformers-bart-model-explained/553 (pristupljeno u junu 2024.)
[10] N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W.Li, P. J. Liu, „Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer“, 2020
[11] https://databasecamp.de/en/ml-blog/t5-model (pristupljeno u junu 2024.)