lexical_match.py

def normalize_answer(s):
    def remove_articles(text):
        return regex.sub(r'\b(a|an|the)\b', ' ', text)

    def white_space_fix(text):
        return ' '.join(text.split())

    def remove_punc(text):
        exclude = set(string.punctuation)
        return ''.join(ch for ch in text if ch not in exclude)

    def lower(text):
        return text.lower()

    return white_space_fix(remove_articles(remove_punc(lower(s))))

def exact_match_score(prediction, ground_truth):
    return normalize_answer(prediction) == normalize_answer(ground_truth)

def ems(prediction, ground_truths):
    return max([exact_match_score(prediction, gt) for gt in ground_truths])

def lexical_match_score(prediction, ground_truth):
    return normalize_answer(ground_truth) in normalize_answer(prediction)

def lms(prediction, ground_truths):
    return max([lexical_match_score(prediction, gt) for gt in ground_truths])