2020
DOI: 10.1609/aaai.v34i05.6477
|View full text |Cite
|
Sign up to set email alerts
|

Improving Domain-Adapted Sentiment Classification by Deep Adversarial Mutual Learning

Abstract: Domain-adapted sentiment classification refers to training on a labeled source domain to well infer document-level sentiment on an unlabeled target domain. Most existing relevant models involve a feature extractor and a sentiment classifier, where the feature extractor works towards learning domain-invariant features from both domains, and the sentiment classifier is trained only on the source domain to guide the feature extractor. As such, they lack a mechanism to use sentiment polarity lying in the target do… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
14
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
3
3
3
1

Relationship

0
10

Authors

Journals

citations
Cited by 31 publications
(14 citation statements)
references
References 17 publications
0
14
0
Order By: Relevance
“…The basic idea for domain adaptation is to learn domain-invariant representations which generalize across the domains. To achieve this, the most prevailing method Domain Adversarial Neural Network (DANN) (Ganin et al, 2016;Qu et al, 2019;Xue et al, 2020) introduces a domain classifier and uses adversarial training to make the features unable to discriminate between source and target domains. This method has been applied to many NLP tasks.…”
Section: Domain Adaptationmentioning
confidence: 99%
“…The basic idea for domain adaptation is to learn domain-invariant representations which generalize across the domains. To achieve this, the most prevailing method Domain Adversarial Neural Network (DANN) (Ganin et al, 2016;Qu et al, 2019;Xue et al, 2020) introduces a domain classifier and uses adversarial training to make the features unable to discriminate between source and target domains. This method has been applied to many NLP tasks.…”
Section: Domain Adaptationmentioning
confidence: 99%
“…Different from several domain adaption methods proposed for sentiment classification (Qu et al, 2019b;Du et al, 2020;Xue et al, 2020;Zhang et al, 2019;He et al, 2018) where the labels in the target domain are not available, both the source and target labels are available in our transfer learning setting. In our setting, we seek to leverage data-sufficient domains to help target domains with less sufficient data labels.…”
Section: Related Workmentioning
confidence: 99%
“…They proposed that the smaller emotion granularity, the more necessary it is to filter important emotions in context. In 2020, Qianming Xue, Wei Zhang et al proposed a domainrecognizer, which uses two feature extractors to detect features of invariant sentiment [21]. Tomoki Ito, Kota Tsubouchi et al proposed an interpretable neural network lexical initialization learning method, judging primitive-level word emotions out of contextfirstly and judging global emotions [22].…”
Section: Related Workmentioning
confidence: 99%