IMPROVING USER EXPERIENCE IN THE IMPLEMENTATION OF THE PUBLIC PROCUREMENT LAW IN THE REPUBLIC OF SERBIA THROUGH AN INTERACTIVE CHATBOT BASED ON AI TECHNOLOGY
Keywords:
Chatbot, neural networks, Python, Public Procurement Law (ZJN), hyperparameters, modeling, BM25Okapi, GPT-2, NLP, wandb, result analysis, model training, virtual consultant, revolution in consulting services, datasetAbstract
This scientific research paper presents the development of a neural network for a computer model that will be applied in the development of a chatbot web application based on a proprietary dataset. The aim of the chatbot is to provide virtual consulting support in the implementation of the Public Procurement Law in the Republic of Serbia. This AI tool is of crucial importance for both procurers and bidders, given the need for understanding and compliance with the law. By using the complete content of texts related to the law's implementation available on the internet, the model will train its neural networks based on an algorithm to provide answers to various questions.
The chatbot will be capable of answering questions related to the definitions of the Public Procurement Law ("What is...?"), procedural questions ("What to do in the following case...?"), and ways to overcome obstacles in implementing the law ("How to overcome the problem...?"). By tracking the conversation context and searching through texts, the model will provide meaningful responses.
This project has the potential to revolutionize the implementation of the Public Procurement Law in Serbia, considering the large number of officials and the lack of consultants who could provide accurate real-time answers and solutions. Currently, there are numerous decisions of the Republic Commission for the Protection of Rights that represent the practice of law implementation, and the chatbot would enable access to this information to ensure the correctness and transparency of public procurement procedures.
Therefore, the model can be expanded and adapted for application with other laws, provided that there is appropriate textual material for model training and tokenization, which would further enhance the accuracy of responses to questions regarding the implementation of the Public Procurement Law.
It is important to note that as the conceptual creator of this concept, I have personally submitted a request to the Institute for Artificial Intelligence - AI Institute Novi Sad, Serbia, to collaborate on realizing this idea.
References
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009). Curriculum learning. Proceedings of the 26th
Annual International Conference on Machine Learning (ICML), 41, 41-48. https://doi.org/10.1145/1553374.1553380
Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of Machine
Learning Research, 13(Feb), 281-305. http://www.jmlr.org/papers/volume13/bergstra12a/bergstra12a.pdf
Brown, T. B., et al. (2020). Language Models are Few-Shot Learners. Advances in Neural Information Processing
Systems 33 (NeurIPS 2020).
Brown, T. B., et al. (2020). Language Models are Few-Shot Learners. arXiv preprint arXiv:2005.14165.
Dai, Z., et al. (2019). Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context. Proceedings
of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019).
Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
https://arxiv.org/abs/1412.6980
Liu, Y., et al. (2020). Generative Pre-trained Transformer 3 (GPT-3). arXiv preprint arXiv:2005.14165.
Liu, Y., et al. (2020). On the Variance of the Adaptive Learning Rate and Beyond. Proceedings of the 7th
International Conference on Learning Representations (ICLR 2019).
Radford, A., et al. (2019). Language Models are Unsupervised Multitask Learners. OpenAI Blog.
Radford, A., et al. (2019). Language Models are Unsupervised Multitask Learners. arXiv preprint
arXiv:1910.10683.
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2019). Language models are
unsupervised multitask learners. OpenAI Blog, 1(8). https://cdn.openai.com/better-language-models/language_models_are_unsupervised_multitask_learners.pdf
Raffel, C., et al. (2020). Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer.
arXiv preprint arXiv:1910.10683.
Sasaki, Y. (2007). The truth of the F-measure. The University of Tokyo. http://acl.ldc.upenn.edu/W/W04/W04-
Vaswani, A., et al. (2017). Attention Is All You Need. Proceedings of the 31st Conference on
Neural Information Processing Systems (NeurIPS 2017).
Wolf, T., et al. (2020). Transformers: State-of-the-Art Natural Language Processing. Proceedings of the 2020
Conference on Empirical Methods in Natural Language Processing (EMNLP 2020).
