English

Strong Baselines for Neural Semi-supervised Learning under Domain Shift

Computation and Language 2018-04-26 v1 Machine Learning Machine Learning

Abstract

Novel neural models have been proposed in recent years for learning under domain shift. Most models, however, only evaluate on a single task, on proprietary datasets, or compare to weak baselines, which makes comparison of models difficult. In this paper, we re-evaluate classic general-purpose bootstrapping approaches in the context of neural networks under domain shifts vs. recent neural approaches and propose a novel multi-task tri-training method that reduces the time and space complexity of classic tri-training. Extensive experiments on two benchmarks are negative: while our novel method establishes a new state-of-the-art for sentiment analysis, it does not fare consistently the best. More importantly, we arrive at the somewhat surprising conclusion that classic tri-training, with some additions, outperforms the state of the art. We conclude that classic approaches constitute an important and strong baseline.

Keywords

Cite

@article{arxiv.1804.09530,
  title  = {Strong Baselines for Neural Semi-supervised Learning under Domain Shift},
  author = {Sebastian Ruder and Barbara Plank},
  journal= {arXiv preprint arXiv:1804.09530},
  year   = {2018}
}

Comments

ACL 2018

R2 v1 2026-06-23T01:35:19.250Z