大语言模型评估指标BLEU,ROUGE,PPL

EmbodiedTech

于 2024-06-26 21:33:29 发布

阅读量486

点赞数 2

CC 4.0 BY-SA版权

文章标签：语言模型人工智能自然语言处理

本文链接：https://blog.csdn.net/Daniel_Singularity/article/details/139998984

# 第一步安装nltk的包-->pip install nltk
from nltk.translate.bleu_score import sentence_bleu

def cumulative_bleu(reference, candidate):

    bleu_1_gram = sentence_bleu(reference, candidate, weights=(1, 0, 0, 0))
    bleu_2_gram = sentence_bleu(reference, candidate, weights=(0.5, 0.5, 0, 0))
    bleu_3_gram = sentence_bleu(reference, candidate, weights=(0.33, 0.33, 0.33, 0))
    bleu_4_gram = sentence_bleu(reference, candidate, weights=(0.25, 0.25, 0.25, 0.25))

    # print('bleu 1-gram: %f' % bleu_1_gram)
    # print('bleu 2-gram: %f' % bleu_2_gram)
    # print('bleu 3-gram: %f' % bleu_3_gram)
    # print('bleu 4-gram: %f' % bleu_4_gram)

    return bleu_1_gram, bleu_2_gram, bleu_3_gram, bleu_4_gram
    # return bleu_1_gram, bleu_2_gram

# 生成文本
candidate_text = ["This", "is",  "some",  "generated", "text"]

# 参考文本列表
reference_texts = [["Th