import torch from transformers import BertTokenizer, BertModel # 加载Bert预训练模型和tokenizer model = BertModel.from_pretrained('bert-base-chinese') tokenizer = BertTokenizer.from_pretrained('bert-base-chinese') # 微博文本和种子词 text = '今天天气真好，心情非常愉快！' seeds = ['天气', '心情', '愉快'] # 将微博文本和种子词转换为Bert输入格式 inputs = tokenizer.encode_plus(text, add_special_tokens=True, return_tensors='pt') seed_inputs = tokenizer.encode_plus(seeds, add_special_tokens=True, return_tensors='pt', padding=True) # 使用Bert模型获取微博文本和种子词的词向量 with torch.no_grad(): text_embeddings = model(inputs['input_ids'], attention_mask=inputs['attention_mask'])[0] # [1, seq_len, hidden_size] seed_embeddings = model(seed_inputs['input_ids'], attention_mask=seed_inputs['attention_mask'])[0] # [batch_size, seq_len, hidden_size] # 计算种子词和微博文本中所有词语的余弦相似度 text_embeddings = text_embeddings.squeeze(0) # [seq_len, hidden_size] seed_embeddings = seed_embeddings.mean(dim=1) # [batch_size, hidden_size] -> [batch_size, 1, hidden_size] -> [batch_size, hidden_size] cosine_similarities = torch.matmul(text_embeddings, seed_embeddings.transpose(0, 1)) # [seq_len, batch_size] # 获取相似度最高的词语 similar_words = [] for i in range(len(seeds)): seed_similarities = cosine_similarities[:, i].tolist() max_sim_idx = seed_similarities.index(max(seed_similarities)) similar_word = tokenizer.convert_ids_to_tokens(inputs['input_ids'][0][max_sim_idx].item()) similar_words.append(similar_word) print(similar_words) 能不能详细讲解一下上述这段代码的每行代码的意思，为什么这样用，比如用到的函数是什么意思，生成的变量是什么类型，能列举吗？而且这段代码中后面的这行代码seed_similarities = cosine_similarities[:, i].tolist()报错了，报错显示Traceback (most recent call last): File "E:/PyCharm Community Edition 2020.2.2/Project/WordDict/cos_similarity.py", line 35, in <module> seed_similarities = cosine_similarities[:, i].tolist() IndexError: index 1 is out of bounds for dimension 1 with size 1 能不能帮我解释一下为什么错，解释一下该怎么修改，并给出修改后的代码呢？
193
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
