H
Hal Daumé
Researcher at University of Maryland, College Park
Publications - 265
Citations - 22341
Hal Daumé is an academic researcher from University of Maryland, College Park. The author has contributed to research in topics: Machine translation & Structured prediction. The author has an hindex of 62, co-authored 261 publications receiving 18655 citations. Previous affiliations of Hal Daumé include University of Southern California & Carnegie Mellon University.
Papers
More filters
Posted Content
Frustratingly Easy Domain Adaptation
TL;DR: In this paper, the authors describe an approach to domain adaptation that is appropriate exactly in the case when one has enough target data to do slightly better than just using only source data.
Proceedings Article
Frustratingly Easy Domain Adaptation
TL;DR: This work describes an approach to domain adaptation that is appropriate exactly in the case when one has enough “target” data to do slightly better than just using only “source’ data.
Posted Content
Datasheets for Datasets
Timnit Gebru,Jamie Morgenstern,Briana Vecchione,Jennifer Wortman Vaughan,Hanna Wallach,Hal Daumé,Kate Crawford +6 more
TL;DR: Documentation to facilitate communication between dataset creators and consumers and consumers is presented.
Proceedings Article
Co-regularized Multi-view Spectral Clustering
TL;DR: A spectral clustering framework is proposed that achieves this goal by co-regularizing the clustering hypotheses, and two co- regularization schemes are proposed to accomplish this.
Journal ArticleDOI
Domain adaptation for statistical classifiers
Hal Daumé,Daniel Marcu +1 more
TL;DR: This work introduces a statistical formulation of this problem in terms of a simple mixture model and presents an instantiation of this framework to maximum entropy classifiers and their linear chain counterparts and leads to improved performance on three real world tasks on four different data sets from the natural language processing domain.