G
Galen Andrew
Researcher at Google
Publications - 27
Citations - 4475
Galen Andrew is an academic researcher from Google. The author has contributed to research in topics: Computer science & Conditional random field. The author has an hindex of 18, co-authored 24 publications receiving 3764 citations. Previous affiliations of Galen Andrew include Stanford University & Microsoft.
Papers
More filters
Proceedings Article
Deep Canonical Correlation Analysis
TL;DR: DCCA is introduced, a method to learn complex nonlinear transformations of two views of data such that the resulting representations are highly linearly correlated and Parameters of both transformations are jointly learned to maximize the (regularized) total correlation.
Proceedings ArticleDOI
Scalable training of L1-regularized log-linear models
Galen Andrew,Jianfeng Gao +1 more
TL;DR: This work presents an algorithm Orthant-Wise Limited-memory Quasi-Newton (OWL-QN), based on L-BFGS, that can efficiently optimize the L1-regularized log-likelihood of log-linear models with millions of parameters.
A Conditional Random Field Word Segmenter for Sighan Bakeoff 2005
TL;DR: A Chinese word segmentation system built using a conditional random field sequence model that provides a framework to use a large number of linguistic features such as character identity, morphological and character reduplication features is presented.
Posted Content
Applied Federated Learning: Improving Google Keyboard Query Suggestions
Timothy Yang,Galen Andrew,Hubert Eichner,Haicheng Sun,Wei Li,Nicholas Kong,Daniel Ramage,Francoise Beaufays +7 more
TL;DR: This paper uses federated learning in a commercial, global-scale setting to train, evaluate and deploy a model to improve virtual keyboard search suggestion quality without direct access to the underlying user data.
Proceedings Article
Tregex and Tsurgeon: tools for querying and manipulating tree data structures.
Roger Levy,Galen Andrew +1 more
TL;DR: This work provides a combined engine for tree query (Tregex) and manipulation (Tsurgeon) that can operate on arbitrary tree data structures with no need for preprocessing.