Distributional semantics
Distributional semantics is a research area that focuses on developing techniques or theories that quantify and categorize semantic similarities between linguistic items based on their distributional properties in large samples of text data.
I want to give an example here that gives you an idea of what I mean by distributional semantics. Suppose you have text data of travelling blogs. Now, you as a person know that pasta, noodles, burgers, and so on are edible food items, whereas juice, tea, coffee, and so on are drinkable items. As a human, we can easily classify drinkable and edible food items because we have a certain context related with each of them, but machines cannot really know these kind of semantics. There ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access