{
  "id": "1911.11756",
  "version": "v1",
  "published": "2019-11-26T18:47:48.000Z",
  "updated": "2019-11-26T18:47:48.000Z",
  "title": "Semi-Supervised Learning for Text Classification by Layer Partitioning",
  "authors": [
    "Alexander Hanbo Li",
    "Abhinav Sethy"
  ],
  "comment": "ASRU 2019",
  "categories": [
    "cs.LG",
    "cs.CL",
    "stat.ML"
  ],
  "abstract": "Most recent neural semi-supervised learning algorithms rely on adding small perturbation to either the input vectors or their representations. These methods have been successful on computer vision tasks as the images form a continuous manifold, but are not appropriate for discrete input such as sentence. To adapt these methods to text input, we propose to decompose a neural network $M$ into two components $F$ and $U$ so that $M = U\\circ F$. The layers in $F$ are then frozen and only the layers in $U$ will be updated during most time of the training. In this way, $F$ serves as a feature extractor that maps the input to high-level representation and adds systematical noise using dropout. We can then train $U$ using any state-of-the-art SSL algorithms such as $\\Pi$-model, temporal ensembling, mean teacher, etc. Furthermore, this gradually unfreezing schedule also prevents a pretrained model from catastrophic forgetting. The experimental results demonstrate that our approach provides improvements when compared to state of the art methods especially on short texts.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2019-11-26T18:47:48.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "text classification",
      "layer partitioning",
      "experimental results demonstrate",
      "computer vision tasks",
      "state-of-the-art ssl algorithms"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}