util_tag.py

# Adapted from seqeval.metrics.sequence_labeling for more control
import warnings


def get_entities(seq):
    """
    Include start tag in return to later identify span starting with 'I' or 'E'.
    :param seq: ['B-PER', 'I-PER', 'O', 'B-LOC']
    :return: [('PER', 0, 1, 'B'), ('LOC', 3, 3, 'B')]
    :rtype: list of (chunk_type, chunk_start, chunk_end, start tag)
    """
    def _validate_chunk(chunk):
        assert chunk in ['O', 'B', 'I', 'E', 'S'] or chunk.startswith(('B-', 'I-', 'E-', 'S-'))

    prev_tag = 'O'
    prev_type = ''
    begin_offset = 0
    begin_tag = 'O'
    chunks = []
    for i, chunk in enumerate(seq + ['O']):
        _validate_chunk(chunk)

        tag = chunk[0]
        type_ = chunk[1:].split('-', maxsplit=1)[-1] or '_'

        if end_of_chunk(prev_tag, tag, prev_type, type_):
            chunks.append((prev_type, begin_offset, i - 1, begin_tag))  # Inclusive
        if start_of_chunk(prev_tag, tag, prev_type, type_):
            begin_offset = i
            begin_tag = tag
        prev_tag = tag
        prev_type = type_

    return chunks


def end_of_chunk(prev_tag, tag, prev_type, type_):
    """Checks if a chunk ended between the previous and current word.
    Args:
        prev_tag: previous chunk tag.
        tag: current chunk tag.
        prev_type: previous type.
        type_: current type.
    Returns:
        chunk_end: boolean.
    """
    chunk_end = False

    if prev_tag == 'E':
        chunk_end = True
    if prev_tag == 'S':
        chunk_end = True

    if prev_tag == 'B' and tag == 'B':
        chunk_end = True
    if prev_tag == 'B' and tag == 'S':
        chunk_end = True
    if prev_tag == 'B' and tag == 'O':
        chunk_end = True
    if prev_tag == 'I' and tag == 'B':
        chunk_end = True
    if prev_tag == 'I' and tag == 'S':
        chunk_end = True
    if prev_tag == 'I' and tag == 'O':
        chunk_end = True

    if prev_tag != 'O' and prev_tag != '.' and prev_type != type_:
        chunk_end = True

    return chunk_end


def start_of_chunk(prev_tag, tag, prev_type, type_):
    """Checks if a chunk started between the previous and current word.
    Args:
        prev_tag: previous chunk tag.
        tag: current chunk tag.
        prev_type: previous type.
        type_: current type.
    Returns:
        chunk_start: boolean.
    """
    chunk_start = False

    if tag == 'B':
        chunk_start = True
    if tag == 'S':
        chunk_start = True

    if prev_tag == 'E' and tag == 'E':
        chunk_start = True
    if prev_tag == 'E' and tag == 'I':
        chunk_start = True
    if prev_tag == 'S' and tag == 'E':
        chunk_start = True
    if prev_tag == 'S' and tag == 'I':
        chunk_start = True
    if prev_tag == 'O' and tag == 'E':
        chunk_start = True
    if prev_tag == 'O' and tag == 'I':
        chunk_start = True

    if tag != 'O' and tag != '.' and prev_type != type_:
        chunk_start = True

    return chunk_start