自然言語処理技術におけるテキスト類似度計算問題

import numpy as np
from gensim.models import Word2Vec

def sentence_similarity(sentence1, sentence2, model):
    vec1 = np.mean([model[word] for word in sentence1 if word in model], axis=0)
    vec2 = np.mean([model[word] for word in sentence2 if word in model], axis=0)
    similarity = np.dot(vec1, vec2) / (np.linalg.norm(vec1) * np.linalg.norm(vec2))
    return similarity

# 加载预训练的Word2Vec模型
model = Word2Vec.load('path/to/word2vec.model')

# 示例句子
sentence1 = '我喜欢吃苹果'
sentence2 = '我不喜欢吃橙子'

similarity = sentence_similarity(sentence1, sentence2, model)
print('句子相似度：', similarity)

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity

def document_similarity(document1, document2):
    tfidf = TfidfVectorizer()
    tfidf_matrix = tfidf.fit_transform([document1, document2])
    similarity = cosine_similarity(tfidf_matrix[0], tfidf_matrix[1])
    return similarity[0][0]

# 示例文档
document1 = '我喜欢吃苹果'
document2 = '我不喜欢吃橙子'

similarity = document_similarity(document1, document2)
print('文档相似度：', similarity)