Professor Bell’s presentation introduces how large language models can be used as tools for investigating word meaning and linguistic structure. Building on the principle that “you shall know a word by the company it keeps”, she explains how distributional semantics underlies both traditional linguistic analysis and modern computational systems. She will present recent work using a large language model to explore links between word meaning and lexical tone in Mandarin Chinese, showing how such models can reveal patterns that support second language learning and deepen our understanding of how meaning is encoded in language. Her talk also offers reflections on how linguists and translators can use these tools responsibly in professional contexts, including considerations for research accuracy, translation consistency, and best practices when integrating AI into linguistic or translation workflows.