Cross-Domain Sentiment Classification with Target Domain Specific Information
Published 1 January 2018Open access
Minlong Peng, Qi Zhang, Yu–Gang Jiang, Xuanjing Huang
Citations93
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This work proposes a method to simultaneously extract domain specific and invariant representations and train a classifier on each of the representation, respectively, and introduces a few target domain labeled data for learning domain-specific information.
Abstract
The task of adopting a model with good performance to a target domain that is different from the source domain used for training has received considerable attention in sentiment analysis. Most existing approaches mainly focus on learning representations that are domain-invariant in both the source and target domains. Few of them pay attention to domain specific information, which should also be informative. In this work, we propose a method to simultaneously extract domain specific and invariant representations and train a classifier on each of the representation, respectively. And we introduce a few target domain labeled data for learning domain-specific information. To effectively utilize the target domain labeled data, we train the domain-invariant representation based classifier with both the source and target domain labeled data and train the domain-specific representation based classifier with only the target domain labeled data. These two classifiers then boost each other in a co-training style. Extensive sentiment analysis experiments demonstrated that the proposed method could achieve better performance than state-of-the-art methods.
Keywords
Computer Science
IEEE Transactions on Knowledge and Data EngineeringA Survey on Transfer Learning
23,164 Citations2009Sinno Jialin Pan, Qiang Yang
The relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift are discussed.
UvA-DARE (University of Amsterdam)Auto-Encoding Variational Bayes
15,628 Citations2013Diederik P. Kingma, Max Welling
A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
Chemometrics and Intelligent Laboratory SystemsPrincipal component analysis
11,538 Citations1987Svante Wold, Kim H. Esbensen +1 more
Advances in computer vision and pattern recognitionDomain-Adversarial Training of Neural Networks
7,498 Citations2017Yaroslav Ganin, Evgeniya Ustinova +6 more
A new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions, which can be achieved in almost any feed-forward model by augmenting it with few standard layers and a new gradient reversal layer.
Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification
2,026 Citations2007John Blitzer, Mark Dredze +1 more
This work extends to sentiment classification the recently-proposed structural correspondence learning (SCL) algorithm, reducing the relative error due to adaptation between domains by an average of 30% over the original SCL algorithm and 46% over a supervised baseline.
The MIT Press eBooksAnalysis of Representations for Domain Adaptation
2,023 Citations2007Shai Ben-David, John Blitzer +2 more
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.
Proceedings of the AAAI Conference on Artificial IntelligenceReturn of Frustratingly Easy Domain Adaptation
1,879 Citations2016Baochen Sun, Jiashi Feng +1 more
This work proposes a simple, effective, and efficient method for unsupervised domain adaptation called CORrelation ALignment (CORAL), which minimizes domain shift by aligning the second-order statistics of source and target distributions, without requiring any target labels.
BioinformaticsIntegrating structured biological data by Kernel Maximum Mean Discrepancy
1,710 Citations2006Karsten Borgwardt, Arthur Gretton +4 more
A novel statistical test of whether two samples are from the same distribution, compatible with both multivariate and structured data, that is fast, easy to implement, and works well, as confirmed by the experiments.
Domain adaptation for large-scale sentiment classification: A deep learning approach
1,563 Citations2011Xavier Glorot, Antoine Bordes +1 more
A deep learning approach is proposed which learns to extract a meaningful representation for each review in an unsupervised fashion and clearly outperform state-of-the-art methods on a benchmark composed of reviews of 4 types of Amazon products.
Unsupervised Visual Domain Adaptation Using Subspace Alignment
1,364 Citations2013Basura Fernando, Amaury Habrard +2 more
This paper introduces a new domain adaptation algorithm where the source and target domains are represented by subspaces described by eigenvectors, and seeks a domain adaptation solution by learning a mapping function which aligns the source subspace with the target one.
arXiv (Cornell University)Domain Separation Networks
765 Citations2016Konstantinos Bousmalis, George Trigeorgis +3 more
arXiv (Cornell University)Domain Separation Networks
587 Citations2016Konstantinos Bousmalis, George Trigeorgis +3 more
The novel architecture results in a model that outperforms the state-of-the-art on a range of unsupervised domain adaptation scenarios and additionally produces visualizations of the private and shared representations enabling interpretation of the domain adaptation process.
Co-Training for Domain Adaptation
360 Citations2011Minmin Chen, Kilian Q. Weinberger +1 more
An algorithm that bridges the gap between source and target domains by slowly adding to the training set both the target features and instances in which the current algorithm is the most confident, and is named CODA (Co-training for domain adaptation).
arXiv (Cornell University)Central Moment Discrepancy (CMD) for Domain-Invariant Representation\n Learning
322 Citations2017Werner Zellinger, Thomas Grubinger +3 more
Data Archiving and Networked Services (DANS)The Variational Fair Autoencoder
271 Citations2016Christos Louizos, Kevin Swersky +3 more
IEEE Transactions on Knowledge and Data EngineeringDomain Invariant Transfer Kernel Learning
222 Citations2014Mingsheng Long, Jianmin Wang +2 more
A transfer kernel learning approach to learn a domain-invariant kernel by directly matching source and target distributions in the reproducing kernel Hilbert space (RKHS) and designs a family of spectral kernels by extrapolating target eigensystem on source samples with Mercer's theorem.
arXiv (Cornell University)Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
214 Citations2017Werner Zellinger, Thomas Grubinger +3 more
Central Moment Discrepancy achieves a new state-of-the-art performance on most domain adaptation tasks of Office and outperforms networks trained with MMD, Variational Fair Autoencoders and Domain Adversarial Neural Networks on Amazon reviews.
UvA-DARE (University of Amsterdam)The Variational Fair Autoencoder
187 Citations2015Christos Louizos, Kevin Swersky +3 more
Landmarks-based kernelized subspace alignment for unsupervised domain adaptation
141 Citations2015Rahaf Aljundi, Rémi Emonet +2 more
A novel unsupervised DA approach based on both subspace alignment and selection of landmarks similarly distributed between the two domains is introduced, showing that this new method outperforms the most recent un supervised DA approaches.
International Journal of Computer VisionAsymmetric and Category Invariant Feature Transformations for Domain Adaptation
119 Citations2014Judy Hoffman, Erik Rodner +3 more
A unified flexible model for both supervised and semi-supervised learning that allows us to learn transformations between domains and develops a joint learning framework for adaptive classifiers, which outperforms competing methods in terms of multi-class accuracy and scalability.