2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information
Login Paper Search My Schedule Paper Index Help

My ICASSP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDSS-5.6
Paper Title Cross-Domain Sentiment Classification With Contrastive Learning and Mutual Information Maximization
Authors Tian Li, Xiang Chen, Peking University, China; Shanghang Zhang, Zhen Dong, Kurt Keutzer, University of California, Berkeley, United States
SessionSS-5: Domain Adaptation for Multimedia Signal Processing
LocationGather.Town
Session Time:Wednesday, 09 June, 13:00 - 13:45
Presentation Time:Wednesday, 09 June, 13:00 - 13:45
Presentation Poster
Topic Special Sessions: Domain Adaptation for Multimedia Signal Processing
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract Existing language models usually require large amount of labeled data and are severely challenged by domain shift. In this work we propose a novel model for cross-domain sentiment classification - CLIM - Contrastive Learning with mutual Information Maximization, to explore the potential of contrastive learning for learning domain-invariant and task-discriminative features. To the best of our knowledge, CLIM is the first to investigate contrastive learning for cross-domain sentiment classification. Due to the scarcity of labels on the target domain, we introduce mutual information maximization (MIM) to explore the features that best support the final prediction. Furthermore, MIM is able to maintain a relatively balanced distribution of the model’s prediction, and enlarge the margin between classes on the target, which increases the model robustness and enables the same classifier to be optimal across domains. Consequently, we achieve new state-of-the-art results on the Amazon-review dataset as well as the Airlines dataset, demonstrating the efficacy of our methods.