A Common Subspace Construction Method in Cross-Domain Sentiment Classification

Zhang, Yuhong; Xu, Xu; Hu, Xuegang

doi:10.2991/esac-15.2015.13

Cited by 4 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…target ). DA methods have been successfully applied to many natural language processing (NLP) tasks such as, Part-of-Speech (POS) tagging (Blitzer et al , 2006; Kübler & Baucom, 2011; Liu & Zhang, 2012; Schnabel & Schütze, 2013), sentiment classification (Blitzer et al , 2007; Li & Zong, 2008; Pan et al , 2010; Bollegala et al , 2015; Zhang et al , 2015), and machine translation (Koehn & Schroeder, 2007). Depending on the availability of labelled data for the target domain, DA methods are categorised into two groups: supervised domain adaptation (SDA) methods that assume the availability of (potentially small) labelled data for the target domain, and unsupervised domain adaptation (UDA) methods that do not.…”

Section: Introductionmentioning

confidence: 99%

A comparative study of pivot selection strategies for unsupervised cross-domain sentiment classification

Cui¹,

Al-Bazzaz²,

Bollegala³

et al. 2018

The Knowledge Engineering Review

View full text Add to dashboard Cite

Selecting pivot features that connect a source domain to a target domain is an important first step in unsupervised domain adaptation (UDA). Although different strategies such as the frequency of a feature in a domain, mutual (or pointwise mutual) information have been proposed in prior work in domain adaptation (DA) for selecting pivots, a comparative study into (a) how the pivots selected using existing strategies differ, and (b) how the pivot selection strategy affects the performance of a target DA task remain unknown. In this paper, we perform a comparative study covering different strategies that use both labelled (available for the source domain only) as well as unlabelled (available for both the source and target domains) data for selecting pivots for UDA. Our experiments show that in most cases pivot selection strategies that use labelled data outperform their unlabelled counterparts, emphasising the importance of the source domain labelled data for UDA. Moreover, pointwise mutual information and frequency-based pivot selection strategies obtain the best performances in two state-of-the-art UDA methods.

show abstract

Section: Introductionmentioning

confidence: 99%

A comparative study of pivot selection strategies for unsupervised cross-domain sentiment classification

Cui¹,

Al-Bazzaz²,

Bollegala³

et al. 2018

The Knowledge Engineering Review

View full text Add to dashboard Cite

show abstract

“…• CSC: The authors of [8] proposed a common subspace construction method for cross-domain sentiment classification called CSC. The source domain and target domain were each from D b .…”

Section: Benchmark Experimentsmentioning

confidence: 99%

Low-Resource Cross-Domain Product Review Sentiment Classification Based on a CNN with an Auxiliary Large-Scale Corpus

Wei

Lin

et al. 2017

Algorithms

View full text Add to dashboard Cite

Abstract:The literature contains several reports evaluating the abilities of deep neural networks in text transfer learning. To our knowledge, however, there have been few efforts to fully realize the potential of deep neural networks in cross-domain product review sentiment classification. In this paper, we propose a two-layer convolutional neural network (CNN) for cross-domain product review sentiment classification (LM-CNN-LB). Transfer learning research into product review sentiment classification based on deep neural networks has been limited by the lack of a large-scale corpus; we sought to remedy this problem using a large-scale auxiliary cross-domain dataset collected from Amazon product reviews. Our proposed framework exhibits the dramatic transferability of deep neural networks for cross-domain product review sentiment classification and achieves state-of-the-art performance. The framework also outperforms complex engineered features used with a non-deep neural network method. The experiments demonstrate that introducing large-scale data from similar domains is an effective way to resolve the lack of training data. The LM-CNN-LB trained on the multi-source related domain dataset outperformed the one trained on a single similar domain.

show abstract

Enhanced cross-domain sentiment classification utilizing a multi-source transfer learning approach

2018

View full text Add to dashboard Cite

A Common Subspace Construction Method in Cross-Domain Sentiment Classification

Cited by 4 publications

References 9 publications

A comparative study of pivot selection strategies for unsupervised cross-domain sentiment classification

A comparative study of pivot selection strategies for unsupervised cross-domain sentiment classification

Low-Resource Cross-Domain Product Review Sentiment Classification Based on a CNN with an Auxiliary Large-Scale Corpus

Enhanced cross-domain sentiment classification utilizing a multi-source transfer learning approach

Contact Info

Product

Resources

About