【李宏毅机器学习课件】21.结构化预测.pdf

Introduction of Structured Learning Hung-yi Lee Structured Learning • We need a more powerful function f • Input and output are both objects with structures • Object: sequence, list, tree, bounding box … f : X  Y X is the space of Y is the space of one kind of object another kind of object In the previous lectures, the input and output are both vectors. Example Application • Speech recognition • X : Speech signal (sequence) → Y: text (sequence) • Translation • X : Mandarin sentence (sequence) → Y: English sentence (sequence) • Syntactic Paring • X : sentence → Y: parsing tree (tree structure) • Object Detection • X : Image → Y: bounding box • Summarization • X : long document → Y: summary (short paragraph) • Retrieval • X : keyword → Y: search result (a list of webpage) Unified Framework Training • Find a function F F : X Y R • F(x,y): evaluate how compatible the objects x and y is Inference (Testing) • Given an object x ~   y arg max F x , y y Y   ~   f : X  Y f x y arg max F x , y y Y Unified Framework – Object Detection •Task description • Using a bounding box to highlight the position of a certain object in an image • E.g. A detector of Haruhi X : Image Y : Bounding Box Haruhi