chunk_sents.py 文件源码

def extract_NNs(chunk, pos):
    """
    Given chunk [(phrase, phrase_type)], e.g., [('the lady', 'NP'), ('with', 'PP'), 'the blue shirt', 'NP'],
    and pos [(word, pos)], e.g., [('man', 'NN')]
    we extract from NPs with stopping, location, color, size words filtered out, 
    and return list of NN words only.
    """
    forbid_wds = stop_words + location_words + color_words + size_words
    NNs = []
    for phrase, ptype in chunk:
        if ptype == 'NP':
            filtered_wds = []
            for wd in phrase.split():
                wd_pos = [p[1] for p in pos if p[0] == wd][0]
                if wd not in forbid_wds and wd_pos != 'JJ' and wd_pos != 'CD':  # we don't need JJ nor CD words neither.
                    filtered_wds += [wd]
            if len(' '.join(filtered_wds)) > 0:
                NNs += [' '.join(filtered_wds)]
    return NNs