data_extractor.py 文件源码

def reverb_wrapper(text, stop=None):
    """
    Function-wrapper for ReVerb binary. Extracts relations
    found in text.
    Input:
        - text: str,
        a piece of text or sentence
        - stop: list,
        list of stopwords to remove from the relations
    Output:
        - total: list,
        list of lists. Each inner list contains one relation in the form
        [subject, predicate, object]
    """
    total = []
    for sent in sent_tokenize(text):
        cmd = 'echo "' + sent + '"' "| ./reverb -q | tr '\t' '\n' | cat -n"
        reverb_dir = settings['load']['path']['reverb']
        result = runProcess(cmd, reverb_dir)
        # Extract relations from reverb output
        result = result[-3:]
        result = [row.split('\t')[1].strip('\n') for row in result]
        # Remove common stopwords from relations
        if stop:
            result = [stopw_removal(res, stop) for res in result]
        total.append(result)
    # Remove empty relations
    total = [t for t in total if t]
    return total