Open AccessProceedings Article
Frustratingly Easy Domain Adaptation
Hal Daumé
- 01 Jun 2007
- pp 256-263
1.7K
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.
read more
Abstract: 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. Our approach is incredibly simple, easy to implement as a preprocessing step (10 lines of Perl!) and outperforms stateof-the-art approaches on a range of datasets. Moreover, it is trivially extended to a multidomain adaptation problem, where one has data from a variety of different domains.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Hierarchical Bayesian Approach for Semi-supervised Discriminative Language Modeling.
Yik-Cheung Tam,Paul Vozila +1 more
- 09 Sep 2012
TL;DR: This work views manual and pseudo-truth transcriptions as two domains, and performs domain adaptation on the discriminative language models via hierarchical Bayesian, in which the domainspecific models share a common prior model.
4
•Posted Content
Cross-Domain Label-Adaptive Stance Detection
TL;DR: In this article, an end-to-end unsupervised framework for out-of-domain prediction of unseen, user-defined labels is proposed, which combines domain adaptation techniques such as mixture of experts and domain-adversarial training with label embeddings.
4
•Posted Content
Domain Adaptation for Neural Networks by Parameter Augmentation
TL;DR: A simple domain adaptation method that can be applied to neural networks trained with a cross-entropy loss, which shows performance improvements over other domain adaptation methods on captioning datasets.
•Dissertation
LDA-based dimensionality reduction and domain adaptation with application to DNA sequence classification
Surbhi Mungre
- 01 Jan 2011
TL;DR: Experimental results show that LDA-based features can be successfully used to perform dimensionality reduction and domain adaptation for DNA sequence classification problems, and apply the proposed approaches on the splice site predication problem.
3
A Survey of Heterogeneous Transfer Learning
Runxue Bao,Yiming Sun,Yuhe Gao,Jindong Wang,Qiang Yang,Haifeng Chen,Zhi-Hong Mao,Xing Xie,Ye Ye +8 more
TL;DR: A comprehensive survey of recent developments in heterogeneous transfer learning methods is presented, offering a systematic guide for future research and covers various application contexts, including Natural Language Processing, Computer Vision, Multimodality, and Biomedicine.
References
•Proceedings Article
Analysis of Representations for Domain Adaptation
Shai Ben-David,John Blitzer,Koby Crammer,Fernando Pereira +3 more
- 04 Dec 2006
TL;DR: The theory illustrates the tradeoffs inherent in designing a representation for domain adaptation and gives a new justification for a recently proposed model which explicitly minimizes the difference between the source and target domains, while at the same time maximizing the margin of the training set.
Domain Adaptation with Structural Correspondence Learning
John Blitzer,Ryan McDonald,Fernando Pereira +2 more
- 22 Jul 2006
TL;DR: This work introduces structural correspondence learning to automatically induce correspondences among features from different domains in order to adapt existing models from a resource-rich source domain to aresource-poor target domain.
Search-based structured prediction
TL;DR: Searn is 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 and comes with a strong, natural theoretical guarantee: good performance on the derived classification problems implies goodperformance on the structured prediction problem.
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.