What company do words keep? Revisiting the distributional semantics of J.R. Firth & Zellig Harris

TL;DR

This paper revisits the foundational theories of distributional semantics by Firth and Harris, revealing their differences and exploring how Firth's culturally grounded view can inform modern NLP models of word meaning.

Contribution

It provides a detailed analysis of Firth and Harris's theories, highlighting their divergence, and proposes practical strategies to incorporate broader cultural context into distributional semantics.

Findings

Firth's theory emphasizes cultural and situational context in word meaning.

Harris's theory focuses on internal linguistic forms and relationships.

Proposed methods include comparative stratification and syntagmatic extension.

Abstract

The power of word embeddings is attributed to the linguistic theory that similar words will appear in similar contexts. This idea is specifically invoked by noting that "you shall know a word by the company it keeps," a quote from British linguist J.R. Firth who, along with his American colleague Zellig Harris, is often credited with the invention of "distributional semantics." While both Firth and Harris are cited in all major NLP textbooks and many foundational papers, the content and differences between their theories is seldom discussed. Engaging in a close reading of their work, we discover two distinct and in many ways divergent theories of meaning. One focuses exclusively on the internal workings of linguistic forms, while the other invites us to consider words in new company - not just with other linguistic elements, but also in a broader cultural and situational context. Contrasting these theories from the perspective of current debates in NLP, we discover in Firth a figure who could guide the field towards a more culturally grounded notion of semantics. We consider how an expanded notion of "context" might be modeled in practice through two different strategies: comparative stratification and syntagmatic extension