Open AccessPosted 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.
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 state-of-the-art approaches on a range of datasets. Moreover, it is trivially extended to a multi-domain 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
•Posted Content
Regularized Bayesian transfer learning for population level etiological distributions.
TL;DR: A parsimonious hierarchical Bayesian transfer learning framework to directly estimate population-level class probabilities in a target domain, using any baseline classifier trained on source-domain, and a small labeled target-domain dataset and introduces a novel shrinkage prior for the transfer error rates.
10
•Posted Content
Improving Robustness and Generality of NLP Models Using Disentangled Representations.
TL;DR: Methods to improve robustness and generality of NLP models from the standpoint of disentangled representation learning are presented and it is shown that models trained with the proposed criteria provide better robusts and domain adaptation ability in a wide range of supervised learning tasks.
10
Towards a continuous modeling of natural language domains
Sebastian Ruder,Parsa Ghaffari,John G. Breslin +2 more
- 01 Nov 2016
TL;DR: The authors proposed representation learning-based models that can adapt to continuous domains and detail how these can be used to investigate variation in language using dialogue modeling as a test bed due to its proximity to language modeling and its social component.
10
Domain-Adaptation Technique for Semantic Role Labeling with Structural Learning
TL;DR: It is shown that domain adaptation for SRL systems can achieve state‐of‐the‐art performance when based on structural learning and exploiting a prior model approach.
10
Towards Careful Practices for Automated Linguistic Analysis of Group Learning
TL;DR: This paper reviews work in progress towards bridging the field of linguistics and its operationalizations of discourse, and that of frameworks for studying collaborative learning that are rooted directly in the learning sciences.
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.
•Posted Content
Search-based Structured Prediction
TL;DR: Searn as mentioned in this paper is a meta-algorithm that transforms complex structured prediction problems into simple classification problems to which any binary classifier may be applied, and it is able to learn prediction functions for any loss function and any class of features.
478
•Proceedings Article
Adaptation of Maximum Entropy Capitalizer: Little Data Can Help a Lo.
Ciprian Chelba,Alex Acero +1 more
- 01 Jul 2004
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.