• Publications
  • Influence
Frustratingly Easy Domain Adaptation
TLDR
We 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. Expand
  • 1,498
  • 128
  • PDF
Co-regularized Multi-view Spectral Clustering
TLDR
We propose a spectral clustering framework that achieves this goal by co-regularizing the clustering hypotheses, and propose two co- regularization schemes to accomplish this. Expand
  • 683
  • 125
  • PDF
Generalized Multiview Analysis: A discriminative latent space
TLDR
This paper presents a general multi-view feature extraction approach that we call Generalized Multiview Analysis or GMA. Expand
  • 581
  • 122
  • PDF
Deep Unordered Composition Rivals Syntactic Methods for Text Classification
TLDR
We present a simple deep neural network that competes with and, in some cases, outperforms such models on sentiment analysis and factoid question answering tasks while taking only a fraction of the training time. Expand
  • 562
  • 89
  • PDF
A Co-training Approach for Multi-view Spectral Clustering
TLDR
We propose a spectral clustering algorithm for the multi-view setting where we have access to multiple views of the data, each of which can be independently used for clustering. Expand
  • 576
  • 75
  • PDF
Search-based structured prediction
TLDR
We present Searn, an algorithm for integrating search and learning to solve complex structured prediction problems such as those that occur in natural language, speech, computational biology, and vision. Expand
  • 527
  • 49
  • PDF
Learning Task Grouping and Overlap in Multi-task Learning
TLDR
We propose a framework for multi-task learning that enables one to selectively share the information across the tasks. Expand
  • 380
  • 48
  • PDF
Learning to Search Better than Your Teacher
TLDR
We provide a new learning to search algorithm, LOLS, which does well relative to the reference policy, but additionally guarantees low regret compared to deviations from the learned policy: a local optimality guarantee. Expand
  • 175
  • 28
  • PDF
Domain Adaptation for Statistical Classifiers
TLDR
The most basic assumption used in statistical learning theory is that training data and test data are drawn from a distribution that is related, but not identical, to the "out-of-domain" distribution of the training data. Expand
  • 791
  • 24
  • PDF
Corpus-Guided Sentence Generation of Natural Images
TLDR
We propose a sentence generation strategy that describes images by predicting the most likely nouns, verbs, scenes and prepositions that make up the core sentence structure. Expand
  • 327
  • 23
  • PDF
...
1
2
3
4
5
...