Ensemble Model for Multi-Source Cross-Domain Sentiment Classification with Little Labeled Data

Kwun Ping Lai, Jackie Chun-Sing Ho, Wai LamWI/IAT 2020 · OpenReview

Abstract

We investigate the problem task of multi-source cross-domain sentiment classification with little labeled data, which is a common problem faced by some online store owners. We propose a knowledge-diverse ensemble model which is capable of automatically capturing important topical knowledge used for cross-domain sentiment classification. Through multiple stages of constructing new pseudo-data for training, it can maintain the diversity of the captured knowledge by different base learners. Experiments on a real-world product review dataset show that our proposed model has a good performance even under the little labeled data constraint.
BibTeX
@inproceedings{lai2020ensemble,
  author = {Kwun Ping Lai and Jackie Chun-Sing Ho and Wai Lam},
  title = {{Ensemble Model for Multi-Source Cross-Domain Sentiment Classification with Little Labeled Data}},
  booktitle = {WI/IAT},
  year = {2020},
  url = {https://openreview.net/forum?id=ObCDY5wd8J},
}

Loading related content...

Figure