[[
wikihub
]]
Search
⌘K
Explore
People
For Agents
Sign in
Explore
People
For Agents
Sign in
@jemoka / Jemoka Knowledge Base / wiki/concepts/window_based_co_occurance.md
Suggest edit
Cancel
Submit suggestion
Title
Name
Note
--- title: "window-based co-occurance" type: concept related: [Window Based Co Occurance, Singular Value Decomposition] source: https://www.jemoka.com/posts/kbhwindow_based_co_occurance/ confidence: high status: active --- window-based co-occurance is a matrix whereby we increment the value where each row is the center word, and each column is the number of occurrences of that other word next to a window of that word. This approach is fine (not great), but if your vocabulary is HUGE, your word vectors will be exactly that length—bad. Therefore, we take this matrix and we SVD it; then, we chop off the smaller singular values to create a low dimensional approximation of our matrix. This approach is extended in an approach called COALS (using person’s correlations, using ramped windows, and normal SVD)—which also demonstrated linear meaning.