Analysis of Traditional and Deep Learning Architectures in NLP: Towards Optimal Solutions
T. Subbulakshmi, Prathiba Lakshmi Narayan, Shreejith Suthraye Gokulnath, R. Suganya, Girish H. Subramanian · 2023
In the ever-evolving landscape of Natural Language Processing (NLP), the development of novel architectures and optimization techniques has been instrumental in advancing the field. This survey paper presents a comprehensive exploration of traditional and deep learning architectures employed in NLP, while also delving into the optimization strategies that enhance their performance. With a primary focus on surveying existing literature, the aim is to provide a holistic view of the landscape of NLP architectures and their associated optimization techniques. Additionally, a novel architecture is introduced that promises to contribute to the ongoing progress in NLP. This architecture, detailed in our full paper, combines the best practices and innovations from traditional and deep learning models to tackle NLP tasks effectively. Through this work, the aim is to contribute to the collective knowledge in NLP and facilitate future advancements in the field.