intents_sample_json.json

{
  "dataset": {
    "type": "classification",
    "format": "json",
    "orient": "records",
    "lines": true,
    "data_path": "sample",
    "train": "sample.json",
    "x": "text",
    "y": "intents",
    "url": "http://lnsigo.mipt.ru/export/datasets/snips_intents/train.json",
    "seed": 42,
    "field_to_split": "train",
    "split_fields": [
      "train",
      "valid"
    ],
    "split_proportions": [
      0.9,
      0.1
    ]
  },
  "chainer": {
    "in": ["x"],
    "in_y": ["y"],
    "pipe": [
      {
        "id": "classes_vocab",
        "name": "default_vocab",
        "fit_on": ["y"],
        "level": "token",
        "save_path": "vocabs/snips_classes.dict",
        "load_path": "vocabs/snips_classes.dict"
      },
      {
        "in": ["x"],
        "in_y": ["y"],
        "out": ["y_predicted"],
        "main": true,
        "name": "intent_model",
        "save_path": "intents/intent_cnn_snips_v2",
        "load_path": "intents/intent_cnn_snips_v2",
        "classes": "#classes_vocab.keys()",
        "opt": {
          "kernel_sizes_cnn": [
            1,
            2,
            3
          ],
          "filters_cnn": 256,
          "lear_metrics": [
            "binary_accuracy",
            "fmeasure"
          ],
          "confident_threshold": 0.5,
          "optimizer": "Adam",
          "lear_rate": 0.01,
          "lear_rate_decay": 0.1,
          "loss": "binary_crossentropy",
          "text_size": 15,
          "coef_reg_cnn": 1e-4,
          "coef_reg_den": 1e-4,
          "dropout_rate": 0.5,
          "epochs": 1000,
          "dense_size": 100,
          "model_name": "cnn_model"
        },
        "embedder": {
          "name": "fasttext",
          "save_path": "embeddings/dstc2_fastText_model.bin",
          "load_path": "embeddings/dstc2_fastText_model.bin",
          "emb_module": "fasttext",
          "dim": 100
        },
        "tokenizer": {
          "name": "nltk_tokenizer",
          "tokenizer": "wordpunct_tokenize"
        }
      }
    ],
    "out": ["y_predicted"]
  },
  "train": {
    "epochs": 100,
    "batch_size": 64,
    "metrics": [
      "sets_accuracy"
    ],
    "validation_patience": 5,
    "val_every_n_epochs": 1,
    "log_every_n_epochs": 1,
    "show_examples": false,
    "validate_best": true,
    "test_best": false
  }
}