utils.py 文件源码

def conll2modeldata(data):
    """
    Converts the document into a dictionary, with the required format for the model.
    Args:
        data: dict with conll string

    Returns: dict like:

    {
      "clusters": [[[1024,1024],[1024,1025]],[[876,876], [767,765], [541,544]]],
      "doc_key": "nw",
      "sentences": [["This", "is", "the", "first", "sentence", "."], ["This", "is", "the", "second", "."]],
      "speakers": [["spk1", "spk1", "spk1", "spk1", "spk1", "spk1"], ["spk2", "spk2", "spk2", "spk2", "spk2"]]
    }

    """

    conll_str = data['conll_str']
    document_state = DocumentState()
    line_list = conll_str.split('\n')
    for line in line_list:
        document = handle_line(line, document_state)
        if document is not None:
            model_file = document
    return model_file