Research Article | Open Access | Download Full Text
Volume 2 | Issue 1 | Year 2024 | Article Id: AIR-V2I1P101 DOI: https://doi.org/10.59232/AIR-V2I1P101
Natural Language Processing and Neurosymbolic AI: The Role of Neural Networks with Knowledge-Guided Symbolic Approaches
Emily Barnes, James Hutson
| Received | Revised | Accepted | Published |
|---|---|---|---|
| 04 Dec 2023 | 28 Dec 2023 | 10 Jan 2024 | 29 Jan 2024 |
Citation
Emily Barnes, James Hutson. “Natural Language Processing and Neurosymbolic AI: The Role of Neural Networks with Knowledge-Guided Symbolic Approaches .” DS Journal of Artificial Intelligence and Robotics, vol. 2, no. 1, pp. 1-13, 2024.
Abstract
Neurosymbolic AI (NeSy AI) represents a groundbreaking approach in the realm of Natural Language Processing (NLP), merging the pattern recognition of neural networks with the structured reasoning of symbolic AI to address the complexities of human language. This study investigates the effectiveness of neurosymbolic AI in providing nuanced understanding and contextually relevant responses, driven by the need to overcome the limitations of existing models in handling complex linguistic tasks and abstract reasoning. Employing a hybrid methodology that combines multimodal contextual modeling with rule-governed inferences and memory activations, the research delves into specific applications like Named Entity Recognition (NER), where architectures such as BiLSTM + CRF demonstrate improved accuracy by analyzing entire sentence contexts. The results affirm the potential of neurosymbolic AI in enhancing linguistic resolutions, semantic ambiguity resolution, and overall language understanding capabilities. Notably, the study showcases the significant strides in improving NER tasks, highlighting this approach’s practical implications and effectiveness. The evolution of neurosymbolic AI, as indicated by this research, exemplifies the ongoing pursuit to create more sophisticated, accurate, and human-like interactions between machines and human language, promising a transformative impact on various sectors, including healthcare and education. The findings pave the way for future research and development in AI, pushing the boundaries of the role of technology in understanding and interacting with human language.
Keywords
Neurosymbolic AI, Natural Language Processing (NLP), Contextual modeling, Semantic ambiguity resolution, Named Entity Recognition (NER).
References
[1] Pascal Hitzler, and Frank van Harmelen, “A Reasonable Semantic Web,” Semantic Web, vol. 1, no. 1-2, pp. 39-44, 2010.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Robin Cowan, “Expert Systems: Aspects of and Limitations to the Codifiability of Knowledge,” Research Policy, vol. 30, no. 9, pp. 1355-1372, 2001.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Kyle Hamilton et al., “Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review,” arXiv, pp. 1-27, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Rabinandan Kishor, “Neuro-Symbolic AI: Bringing a New Era of Machine Learning,” International Journal of Research Publication and Reviews, vol. 3, no. 12, pp. 2326-2336, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Vamsi Krishna Vedantam, “The Survey: Advances in Natural Language Processing Using Deep Learning,” Turkish Journal of Computer and Mathematics Education (TURCOMAT), vol. 12, no. 4, pp. 1035-1040, 2021.
[Google Scholar] [Publisher Link]
[6] D. Deepa, “Bidirectional Encoder Representations from Transformers (BERT) Language Model for Sentiment Analysis Task,” Turkish Journal of Computer and Mathematics Education (TURCOMAT), vol. 12, no. 7, pp. 1708-1721, 2021.
[Google Scholar] [Publisher Link]
[7] Wahab Khan et al., “Exploring the Frontiers of Deep Learning and Natural Language Processing: A Comprehensive Overview of Key Challenges and Emerging Trends,” Natural Language Processing Journal, vol. 4, pp. 1-31, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Michael A. Arbib, “Warren McCulloch’s Search for the Logic of the Nervous System,” Perspectives in Biology and Medicine, vol. 43, no. 2, pp. 193-216, 2000.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Artur d'Avila Garcez, and Luis Lamb, “Neurosymbolic AI: The 3rd Wave,” Artificial Intelligence Review, pp. 1-37, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Amit Sheth, Kaushik Roy, and Manas Gaur, “Neurosymbolic Artificial Intelligence (Why, What, and How),” IEEE Intelligent Systems, vol. 38, no. 3, pp. 56-62, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[11] David E. Rumelhart, Geoffrey E. Hinton, and Ronald J. Williams, “Learning Representations by Back-Propagating Errors,” Nature, pp. 533-536, 1986.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Alexiei Dingli, and David Farrugia, Neuro-Symbolic AI: Design Transparent and Trustworthy Systems that Understand the World as You do, Packt Publishing, pp. 1-196, 2023.
[Google Scholar] [Publisher Link]
[13] Artur S. D’Avila Garcez, Luís C. Lamb, and Dov M. Gabbay, Neural-Symbolic Cognitive Reasoning, Springer, pp. 1-197, 2009.
[Google Scholar] [Publisher Link]
[14] Artur d'Avila Garcez et al., “Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning,” arXiv, pp. 1-27, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Luca Alessandro Dombetzki, “An Overview over Capsule Networks,” Network Architectures and Services, pp. 89-95, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Michael Hersche et al., “A Neuro-Vector-Symbolic Architecture for Solving Raven’s Progressive Matrices,” Nature Machine Intelligence, vol. 5, pp. 363-375, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Mara Graziani et al., “A Global Taxonomy of Interpretable AI: Unifying the Terminology for the Technical and Social Sciences,” Artificial Intelligence Review, vol. 56, pp. 3473-3504, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Emmanuel Bengio et al., “Conditional Computation in Neural Networks for Faster Models,” arXiv, pp. 1-12, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Mara Graziani et al., “A Global Taxonomy of Interpretable AI: Unifying the Terminology for the Technical and Social Sciences,” Artificial Intelligence Review, vol. 56, pp. 3473-3504, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Hao Zheng et al., “Improving Deep Neural Networks Using Softplus Units,” 2015 International Joint Conference on Neural Networks (IJCNN), Killarney, pp. 1-4, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Ashish Vaswani et al., “Attention is all you need,” 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA, pp. 1-11, 2017.
[Google Scholar] [Publisher Link]
[22] Dongran Yu et al., “A Survey on Neural-Symbolic Learning Systems,” Neural Networks, vol. 166, pp. 105-126, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Roy Bar-Haim et al., “Project Debater APIs: Decomposing the AI Grand Challenge,” arXiv, pp. 1-8, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Samriddhi Srivastav et al., “ChatGPT in Radiology: The Advantages and Limitations of Artificial Intelligence for Medical Imaging Diagnosis,” Cureus, vol. 15, no. 7, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Judith E. Dayhoff, and James M. DeLeo, “Artificial Neural Networks: Opening the Black Box,” Cancer: Interdisciplinary International Journal of the American Cancer Society, vol. 91, no. S8, pp. 1615-1635, 2001.