mlsanityData to 7 Oct 2026

Unsupervised Sentiment Analysis by Transferring Multi-source Knowledge

arXiv 2105.11902 ↗First posted 9 May 2021cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Sentiment analysis (SA) is an important research area in cognitive computation-thus in-depth studies of patterns of sentiment analysis are necessary. At present, rich resource data-based SA has been well developed, while the more challenging and practical multi-source unsupervised SA (i.e. a target domain SA by transferring from multiple source domains) is seldom studied. The challenges behind this problem mainly locate in the lack of supervision information, the semantic gaps among domains (i.e., domain shifts), and the loss of knowledge. However, existing methods either lack the distinguishable capacity of the semantic gaps among domains or lose private knowledge. To alleviate these problems, we propose a two-stage domain adaptation framework. In the first stage, a multi-task methodology-based shared-private architecture is employed to explicitly model the domain common features and the domain-specific features for the labeled source domains. In the second stage, two elaborate mechanisms are embedded in the shared private architecture to transfer knowledge from multiple source domains. The first mechanism is a selective domain adaptation (SDA) method, which transfers knowledge from the closest source domain. And the second mechanism is a target-oriented ensemble (TOE) method, in which knowledge is transferred through a well-designed ensemble method. Extensive experiment evaluations verify that the performance of the proposed framework outperforms unsupervised state-of-the-art competitors. What can be concluded from the experiments is that transferring from very different distributed source domains may degrade the target-domain performance, and it is crucial to choose the proper source domains to transfer from.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 67 references that are in the map. First posted on arXiv 9 May 2021.

Builds on

30 of 67 references.

References · 30

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  4. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  7. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,548
  8. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
  9. 2017Wasserstein GANcited by 635
  10. 2017Tensor Fusion Network for Multimodal Sentiment Analysiscited by 429
  11. 2016Domain Separation Networkscited by 317
  12. 2016Recurrent Neural Network for Text Classification with Multi-Task Learningcited by 144
18 more
  1. 2018Deep Learning for Sentiment Analysis : A Surveycited by 139
  2. 2017Adversarial Multi-task Learning for Text Classificationcited by 91
  3. 2016Beyond Sharing Weights for Deep Domain Adaptationcited by 80
  4. 2018Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approachcited by 63
  5. 2018Multinomial Adversarial Networks for Multi-Domain Text Classificationcited by 40
  6. 2018Adversarial Noise Layer: Regularize Neural Network By Adding Noisecited by 25
  7. 2016The Evolution of Sentiment Analysis - A Review of Research Topics, Venues, and Top Cited Paperscited by 20
  8. 2018Meta Multi-Task Learning for Sequence Modelingcited by 18
  9. 2018SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptationcited by 11
  10. 2017Multiple Source Domain Adaptation with Adversarial Training of Neural Networkscited by 10
  11. 2018Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Taskscited by 9
  12. 2019Additive Adversarial Learning for Unbiased Authenticationcited by 9
  13. 2019Low-rank Kernel Learning for Graph-based Clusteringcited by 7
  14. 2020Relation-Guided Representation Learningcited by 7
  15. 2016Deep Multi-Task Learning with Shared Memorycited by 5
  16. 2018DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classificationcited by 5
  17. 2018Multi-Source Cross-Lingual Model Transfer: Learning What to Sharecited by 2
  18. 2016Unsupervised Domain Adaptation Using Approximate Label Matchingcited by 1

Built on by

Not cited yet.