What company do words keep? Revisiting the distributional semantics of J.R. Firth & Zellig Harris
This work addresses a gap in NLP by clarifying foundational linguistic theories, potentially influencing how semantics is modeled for more culturally aware applications.
The paper revisits the distributional semantics theories of J.R. Firth and Zellig Harris, revealing two distinct and divergent approaches to meaning, and proposes that Firth's theory could guide NLP toward a more culturally grounded semantics by expanding the notion of context through strategies like comparative stratification and syntagmatic extension.
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