utils_claimset.py 文件源码

def nltk_extract_claims(text):
    """
    Attempts to extract claims as a list from a large text string.
    Uses nltk sent_tokenize function in tokenize library
    param string text: string containing several claims
    """
    sent_list = sent_tokenize(text)
    # On a test string this returned a list with the claim number
    # and then the claim text as separate items
    claims_list = []
    for i in range(0, len(sent_list), 2):
        try:
            number = int(sent_list[i].split(".")[0])
        except:
            number = 0

        claims_list.append(
            (number, sent_list[i+1])
        )

    return claims_list