14THE DISTRIBUTIONAL HYPOTHESIS
What is the distributional hypothesis in natural language processing (NLP)? Where is it used, and how far does it hold true?
The distributional hypothesis is a linguistic theory suggesting that words occurring in the same contexts tend to have similar meanings, according to the original source, “Distributional Structure” by Zellig S. Harris. Succinctly, the more similar the meanings of two words are, the more often they appear in similar contexts.
Consider the sentence in Figure 14-1, for example. The words cats and dogs often occur in similar contexts, and we could replace cats with dogs without making the sentence ...
Get Machine Learning Q and AI now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
