@InProceedings{liu-EtAl:2018:W18-34,
  author    = {Liu, Mingkuan  and  Wen, Musen  and  Kopru, Selcuk  and  Liu, Xianjing  and  Lu, Alan},
  title     = {Semi-Supervised Learning with Auxiliary Evaluation Component for Large Scale e-Commerce Text Classification},
  booktitle = {Proceedings of the Workshop on Deep Learning Approaches for Low-Resource NLP},
  month     = {July},
  year      = {2018},
  address   = {Melbourne},
  publisher = {Association for Computational Linguistics},
  pages     = {68--76},
  abstract  = {The lack of high-quality labeled training data has been one of the critical challenges facing many industrial machine learning tasks. To tackle this challenge, in this paper, we propose a semi-supervised learning method to utilize unlabeled data and user feedback signals to improve the performance of ML models. The method employs a primary model Main and an auxiliary evaluation model Eval, where Main and Eval models are trained iteratively by automatically generating labeled data from unlabeled data and/or users’ feedback signals. The proposed approach is applied to different text classification tasks. We report results on both the publicly available Yahoo! Answers dataset and our e-commerce product classification dataset. The experimental results show that the proposed method reduces the classification error rate by 4% and up to 15% across various experimental setups and datasets. A detailed comparison with other semi-supervised learning approaches is also presented later in the paper. The results from various text classification tasks demonstrate that our method outperforms those developed in previous related studies.},
  url       = {http://www.aclweb.org/anthology/W18-3409}
}