metrics.py

# ====================================================
# @Time    : 13/9/20 4:19 PM
# @Author  : Xiao Junbin
# @Email   : junbin@comp.nus.edu.sg
# @File    : metrics.py
# ====================================================
from nltk.tokenize import word_tokenize
from nltk.corpus import wordnet
import numpy as np

def wup(word1, word2, alpha):
    """
    calculate the wup similarity
    :param word1:
    :param word2:
    :param alpha:
    :return:
    """
    # print(word1, word2)
    if word1 == word2:
        return 1.0

    w1 = wordnet.synsets(word1)
    w1_len = len(w1)
    if w1_len == 0: return 0.0
    w2 = wordnet.synsets(word2)
    w2_len = len(w2)
    if w2_len == 0: return 0.0

    #match the first
    word_sim = w1[0].wup_similarity(w2[0])
    if word_sim is None:
        word_sim = 0.0

    if word_sim < alpha:
        word_sim = 0.1*word_sim
    return word_sim


def wups(words1, words2, alpha):
    """

    :param pred:
    :param truth:
    :param alpha:
    :return:
    """
    sim = 1.0
    flag = False
    for w1 in words1:
        max_sim = 0
        for w2 in words2:
            word_sim = wup(w1, w2, alpha)
            if word_sim > max_sim:
                max_sim = word_sim
        if max_sim == 0: continue
        sim *= max_sim
        flag = True
    if not flag:
        sim = 0.0
    return sim


def get_wups(pred, truth, alpha):
    """
    calculate the wups score
    :param pred:
    :param truth:
    :return:
    """
    pred = word_tokenize(pred)
    truth = word_tokenize(truth)
    item1 = wups(pred, truth, alpha)
    item2 = wups(truth, pred, alpha)
    value = min(item1, item2)
    return value