Operationalising Representation in Natural Language Processing

Abstract

Despite its centrality in the philosophy of cognitive science, there has been little prior philosophical work engaging with the notion of representation in contemporary NLP practice. This paper attempts to fill that lacuna: drawing on ideas from cognitive science, I introduce a framework for evaluating the representational claims made about components of neural NLP models, proposing three criteria with which to evaluate whether a component of a model represents a property and operationalising these criteria using probing classifiers, a popular analysis technique in NLP (and deep learning more broadly). The project of operationalising a philosophically-informed notion of representation should be of interest to both philosophers of science and NLP practitioners. It affords philosophers a novel testing-ground for claims about the nature of representation, and helps NLPers organise the large literature on probing experiments, suggesting novel avenues for empirical research.

Forthcoming in the British Journal for the Philosophy of Science (BJPS)

References in corpus (1)

• Operationalising Representation in Natural Language Processing

Cited by in corpus (5)

• Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks
• Standards for Belief Representations in LLMs
• Operationalising Representation in Natural Language Processing
• Chatting with Bots: AI, Speech Acts, and the Edge of Assertion
• Can structural correspondences ground real world representational content in Large Language Models?