76-807 Topics in Literary & Cultural Studies
9–12 units, Carnegie Mellon University
Recent advances in natural language processing (NLP), primarily powered by large language models (LLMs) show great potential for enabling advanced text analysis across a diverse array of applications — from accelerating scientific discovery by automatically analyzing materials science research literature, to facilitating a study of the evolution of narrative arcs in 20th century literature. However, in many cases there remains a significant gap between the promise of modern language technologies, where models are typically benchmarked on a relatively limited set of representative "general purpose" tasks, and the successful deployment of these tools for real-world applications. In practice, each domain-specific task requires special consideration and/or adaptation, often consisting of task definition and dataset curation, experimentation to identify strengths and limitations of existing off-the-shelf methods, and the formulation of an appropriate and computationally/financially feasible plan for adapting available affordances to fit the new domain or task of interest. In this class, students with concentrations outside of NLP (e.g. degree programs in materials science or English) and students with concentrations in or near NLP (LTI, MLD or equivalent expertise) will work with and learn from each other to bridge this gap. Together, students will explore: - Technical foundations for using language technologies, AI literacy and effective science communication; - Acquiring and curating data appropriate to a specific task, evaluation; - Identifying strengths and limitations of various approaches for adaptation to a specific domain or setting, and; - Devising and executing a plan to accomplish research and analysis tasks given said goal.
Prerequisites: none listed
Offered: Fall 2025
Courseweave needs JavaScript to show sections, workloads and planning tools.