Artificial Intelligence in English Linguistics: A Computational Approach to Syntax and Semantics

Abstract

This study investigates the intersection of artificial intelligence and English linguistics through a computational lens, focusing on the modeling of syntax and semantics. Despite significant advancements in machine learning and large-scale language models, challenges persist in achieving robust natural language understanding. The paper presents a structured survey of syntactic and semantic resources, formal grammar frameworks, and neural architectures, emphasizing their relevance to English language processing. It explores the evolution from rule-based systems to deep learning models, including probing techniques and representation learning in BERT, , and T5. Furthermore, the study examines lexical, compositional, and pragmatic semantics, highlighting their integration in modern NLP tasks such as semantic role labeling and question answering. By synthesizing theoretical foundations with empirical benchmarks, the research offers a comprehensive overview of current approaches and identifies key directions for advancing semantic consistency and syntactic generalization in AI-driven language systems.