|
{ |
|
"dataset_reader": { |
|
"type": "conll2003", |
|
"coding_scheme": "BIOUL", |
|
"tag_label": "ner", |
|
"token_indexers": { |
|
"elmo": { |
|
"type": "elmo_characters" |
|
}, |
|
"token_characters": { |
|
"type": "characters", |
|
"min_padding_length": 3 |
|
}, |
|
"tokens": { |
|
"type": "single_id", |
|
"lowercase_tokens": true |
|
} |
|
} |
|
}, |
|
"model": { |
|
"type": "crf_tagger", |
|
"dropout": 0.5, |
|
"encoder": { |
|
"type": "lstm", |
|
"bidirectional": true, |
|
"dropout": 0.5, |
|
"hidden_size": 200, |
|
"input_size": 1202, |
|
"num_layers": 2 |
|
}, |
|
"include_start_end_transitions": false, |
|
"label_encoding": "BIOUL", |
|
"regularizer": { |
|
"regexes": [ |
|
[ |
|
"scalar_parameters", |
|
{ |
|
"alpha": 0.1, |
|
"type": "l2" |
|
} |
|
] |
|
] |
|
}, |
|
"text_field_embedder": { |
|
"token_embedders": { |
|
"elmo": { |
|
"type": "elmo_token_embedder", |
|
"do_layer_norm": false, |
|
"dropout": 0, |
|
"options_file": "lysandre/elmo-2x4096_512_2048cnn_2xhighway/options.json", |
|
"weight_file": "lysandre/elmo-2x4096_512_2048cnn_2xhighway/weights.hdf5" |
|
}, |
|
"token_characters": { |
|
"type": "character_encoding", |
|
"embedding": { |
|
"embedding_dim": 16 |
|
}, |
|
"encoder": { |
|
"type": "cnn", |
|
"conv_layer_activation": "relu", |
|
"embedding_dim": 16, |
|
"ngram_filter_sizes": [ |
|
3 |
|
], |
|
"num_filters": 128 |
|
} |
|
}, |
|
"tokens": { |
|
"type": "embedding", |
|
"embedding_dim": 50, |
|
"pretrained_file": "https://allennlp.s3.amazonaws.com/datasets/glove/glove.6B.50d.txt.gz", |
|
"trainable": true |
|
} |
|
} |
|
} |
|
}, |
|
"train_data_path": "/mnt/tank/dirkg/data/conll2003/train.txt", |
|
"validation_data_path": "/mnt/tank/dirkg/data/conll2003/valid.txt", |
|
"trainer": { |
|
"checkpointer": { |
|
"num_serialized_models_to_keep": 3 |
|
}, |
|
"grad_norm": 5, |
|
"num_epochs": 75, |
|
"optimizer": { |
|
"type": "adam", |
|
"lr": 0.001 |
|
}, |
|
"patience": 25, |
|
"validation_metric": "+f1-measure-overall" |
|
}, |
|
"data_loader": { |
|
"batch_size": 64 |
|
} |
|
} |