# 🤖 PIPELINE DEFINITION

nlp:

  "@core": pipeline

  lang: eds

  components:

    normalizer:

      '@factory': eds.normalizer

    sentencizer:

      '@factory': eds.sentences

    covid:

      '@factory': eds.covid

    qualifier:

      '@factory': eds.span_classifier

      attributes: { "_.negation": [ "sosy" ] }

      span_getter: ["ents", "gold_spans"]

      context_getter: { '@misc': eds.span_context_getter, "context_words": 30, "context_sents": 1 }

      embedding:

        '@factory': eds.span_pooler

        embedding:

          '@factory': eds.text_cnn

          kernel_sizes: [ 3 ]

          embedding:

            '@factory': eds.transformer

            model: hf-internal-testing/tiny-bert

            window: 128

            stride: 96

# 📈 SCORERS

scorer:

  speed: true

  qual:

    '@metrics': "eds.span_attributes"

    span_getter: ${nlp.components.qualifier.span_getter}

    qualifiers: ${nlp.components.qualifier.attributes}

# 🎛️ OPTIMIZER

# (disabled to test the default optimizer)

# optimizer:

#   "@optimizers": adam

#   groups:

#     "*.transformer.*":

#       lr: 1e-3

#       schedules:

#         "@schedules": linear

#         "warmup_rate": 0.1

#         "start_value": 0

#     "*":

#       lr: 1e-3

#       schedules:

#         "@schedules": linear

#         "warmup_rate": 0.1

#         "start_value": 1e-3

# 📚 DATA

train_data:

  data:

    "@readers": json

    path: ./dataset.jsonl

    converter:

      - '@factory': 'myproject.custom_dict2doc'

        span_setter : 'gold_spans'

        span_attributes : ['negation']

        bool_attributes : ['negation']  # default json to doc converter

      - '@factory': eds.sentences

        nlp: ${nlp}

      # - '@factory': eds.split

      #   nlp: null

      #   max_length: 10

      #   randomize: 0.3

      #   # sentence regex:

      #   regex: '\\s*(?:\\n\\s*)+()[A-Z]|[.!?]\\s+()[A-Z]'

        # regex: '\\n{2,}'

  shuffle: dataset

  batch_size: 4 docs

  pipe_names: [ "qualifier" ]

  sub_batch_size: 10 words

val_data:

  "@readers": json

  path: ./dataset.jsonl

  converter:

    - '@factory': myproject.custom_dict2doc

      span_setter : 'gold_spans'

      span_attributes : ['negation']

      bool_attributes : ['negation']  # default standoff to doc converter

# 🚀 TRAIN SCRIPT OPTIONS

train:

  nlp: ${ nlp }

  train_data: ${ train_data }

  val_data: ${ val_data }

  max_steps: 40

  validation_interval: 10

  max_grad_norm: 1.0

  scorer: ${ scorer }

  num_workers: 1