{
  "id": "1804.09530",
  "version": "v1",
  "published": "2018-04-25T13:06:29.000Z",
  "updated": "2018-04-25T13:06:29.000Z",
  "title": "Strong Baselines for Neural Semi-supervised Learning under Domain Shift",
  "authors": [
    "Sebastian Ruder",
    "Barbara Plank"
  ],
  "comment": "ACL 2018",
  "categories": [
    "cs.CL",
    "cs.LG",
    "stat.ML"
  ],
  "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2018-04-25T13:06:29.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "domain shift",
      "strong baseline",
      "neural semi-supervised learning",
      "re-evaluate classic general-purpose bootstrapping approaches",
      "classic approaches constitute"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}