frustratingly easy domain adaptation hal daume iii
TRANSCRIPT
![Page 1: Frustratingly Easy Domain Adaptation Hal Daume III](https://reader036.vdocument.in/reader036/viewer/2022082421/56649d145503460f949e88d6/html5/thumbnails/1.jpg)
Frustratingly Easy Domain Adaptation
Hal Daume III
![Page 2: Frustratingly Easy Domain Adaptation Hal Daume III](https://reader036.vdocument.in/reader036/viewer/2022082421/56649d145503460f949e88d6/html5/thumbnails/2.jpg)
Introduction
• Task: Developing Learning Algorithms that can be easily ported from one domain to another. Example: from newswire to biomedical docs.
• particularly interesting in NLP.• Idea: Transforming the domain adaptation learning
problem into a standard supervised learning problem to which any standard algorithm may be applied (eg., maxent, SVM)
• Transformation is simple – Augment the feature space of both the source and target data and use the result as input to a standard learning algorithm.
![Page 3: Frustratingly Easy Domain Adaptation Hal Daume III](https://reader036.vdocument.in/reader036/viewer/2022082421/56649d145503460f949e88d6/html5/thumbnails/3.jpg)
Problem Formalization
Notation:• X the input space (typically either a real vector or a
binary vector) and Y the output space.• Ds to denote the distribution over source examples and
Dt to denote the distribution over target examples.• we have access to a samples Ds D∼ s of source
examples from the source domain, and samples Dt D∼ t of target examples from the target domain.
• assume that Ds is a collection of N examples and Dt is a collection of M examples (where, typically, N M).≫
• Goal: to learn a function h : X → Y with low expected loss with respect to the target domain.
![Page 4: Frustratingly Easy Domain Adaptation Hal Daume III](https://reader036.vdocument.in/reader036/viewer/2022082421/56649d145503460f949e88d6/html5/thumbnails/4.jpg)
Adaptation by Feature Augmentation
• Take each feature in the original problem and make three versions of it: a general version, a source-specific version and a target-specific version.
• Augmented source data = General and source specific• Augmented Target data = General and target specific
![Page 5: Frustratingly Easy Domain Adaptation Hal Daume III](https://reader036.vdocument.in/reader036/viewer/2022082421/56649d145503460f949e88d6/html5/thumbnails/5.jpg)
Results
• Tasks (see paper)
![Page 6: Frustratingly Easy Domain Adaptation Hal Daume III](https://reader036.vdocument.in/reader036/viewer/2022082421/56649d145503460f949e88d6/html5/thumbnails/6.jpg)
Experimental Results
• See paper