{"id":904,"date":"2025-01-12T10:05:56","date_gmt":"2025-01-12T02:05:56","guid":{"rendered":"https:\/\/www.laixuexila.com\/?p=904"},"modified":"2025-01-12T10:05:56","modified_gmt":"2025-01-12T02:05:56","slug":"%e5%a6%82%e4%bd%95%e7%94%a8python%e5%ae%9e%e7%8e%b0%e8%87%aa%e7%84%b6%e8%af%ad%e8%a8%80%e5%a4%84%e7%90%86%ef%bc%88nlp%ef%bc%89%ef%bc%9a%e5%b7%a5%e5%85%b7%e4%b8%8e%e6%8a%80%e5%b7%a7","status":"publish","type":"post","link":"https:\/\/www.laixuexila.com\/index.php\/2025\/01\/12\/%e5%a6%82%e4%bd%95%e7%94%a8python%e5%ae%9e%e7%8e%b0%e8%87%aa%e7%84%b6%e8%af%ad%e8%a8%80%e5%a4%84%e7%90%86%ef%bc%88nlp%ef%bc%89%ef%bc%9a%e5%b7%a5%e5%85%b7%e4%b8%8e%e6%8a%80%e5%b7%a7\/","title":{"rendered":"\u5982\u4f55\u7528Python\u5b9e\u73b0\u81ea\u7136\u8bed\u8a00\u5904\u7406\uff08NLP\uff09\uff1a\u5de5\u5177\u4e0e\u6280\u5de7"},"content":{"rendered":"\n
\n

\u81ea\u7136\u8bed\u8a00\u5904\u7406\uff08NLP\uff09\u662f\u8ba1\u7b97\u673a\u79d1\u5b66\u3001\u4eba\u5de5\u667a\u80fd\u548c\u8bed\u8a00\u5b66\u4ea4\u53c9\u7684\u9886\u57df\uff0c\u5b83\u4f7f\u5f97\u8ba1\u7b97\u673a\u80fd\u591f\u7406\u89e3\u3001\u5206\u6790\u3001\u751f\u6210\u548c\u4e0e\u4eba\u7c7b\u8bed\u8a00\u8fdb\u884c\u4ea4\u4e92\u3002\u4f7f\u7528Python\u8fdb\u884cNLP\uff0c\u9664\u4e86\u7406\u8bba\u77e5\u8bc6\uff0c\u8fd8\u9700\u8981\u638c\u63e1\u76f8\u5173\u5de5\u5177\u548c\u6280\u5de7\u3002\u4ee5\u4e0b\u662f\u4e00\u4e2a\u4ece\u57fa\u7840\u5230\u8fdb\u9636\u7684\u5b66\u4e60\u8def\u5f84\uff0c\u5e2e\u52a9\u4f60\u5feb\u901f\u638c\u63e1\u5982\u4f55\u7528Python\u5b9e\u73b0NLP\u3002<\/p>\n<\/blockquote>\n\n\n\n

\u4e00\u3001\u57fa\u7840\u90e8\u5206\uff1aNLP\u57fa\u7840\u77e5\u8bc6\u4e0e\u5de5\u5177<\/h3>\n\n\n\n

1. Python\u57fa\u7840\u5e93<\/strong><\/h4>\n\n\n\n
    \n
  • Numpy<\/strong>\uff1a\u7528\u4e8e\u5904\u7406\u6587\u672c\u6570\u636e\u7684\u5411\u91cf\u5316\u64cd\u4f5c\u3002<\/li>\n\n\n\n
  • Pandas<\/strong>\uff1a\u7528\u4e8e\u5904\u7406\u548c\u5206\u6790\u7ed3\u6784\u5316\u6570\u636e\uff0c\u5982\u6587\u672c\u6587\u4ef6\u4e2d\u7684\u6570\u636e\u3002<\/li>\n\n\n\n
  • Matplotlib\/Seaborn<\/strong>\uff1a\u7528\u4e8e\u6570\u636e\u53ef\u89c6\u5316\uff0c\u5e2e\u52a9\u7406\u89e3\u6570\u636e\u7684\u5206\u5e03\u548c\u7edf\u8ba1\u7279\u5f81\u3002<\/li>\n<\/ul>\n\n\n\n

    2. NLP\u4e13\u7528\u5e93<\/strong><\/h4>\n\n\n\n
      \n
    • NLTK\uff08Natural Language Toolkit\uff09<\/strong>\uff1a\u4e00\u4e2a\u5f3a\u5927\u7684NLP\u5de5\u5177\u5e93\uff0c\u63d0\u4f9b\u4e86\u8bcd\u6c47\u3001\u8bed\u6cd5\u3001\u8bed\u4e49\u5206\u6790\u7b49\u529f\u80fd\u3002<\/li>\n\n\n\n
    • spaCy<\/strong>\uff1a\u4e00\u4e2a\u5de5\u4e1a\u7ea7NLP\u5e93\uff0c\u652f\u6301\u6587\u672c\u6807\u6ce8\u3001\u8bcd\u6027\u6807\u6ce8\u3001\u547d\u540d\u5b9e\u4f53\u8bc6\u522b\uff08NER\uff09\u3001\u4f9d\u5b58\u89e3\u6790\u7b49\u3002<\/li>\n\n\n\n
    • TextBlob<\/strong>\uff1a\u4e00\u4e2a\u7b80\u5355\u6613\u7528\u7684NLP\u5e93\uff0c\u9002\u5408\u521d\u5b66\u8005\uff0c\u652f\u6301\u60c5\u611f\u5206\u6790\u3001\u7ffb\u8bd1\u3001\u8bcd\u6027\u6807\u6ce8\u7b49\u3002<\/li>\n\n\n\n
    • Gensim<\/strong>\uff1a\u7528\u4e8e\u5904\u7406\u8bdd\u9898\u6a21\u578b\u548c\u6587\u6863\u76f8\u4f3c\u5ea6\u7b49\u4efb\u52a1\uff0c\u7279\u522b\u9002\u5408\u5927\u89c4\u6a21\u6587\u672c\u6570\u636e\u3002<\/li>\n\n\n\n
    • Transformers\uff08Hugging Face\uff09<\/strong>\uff1a\u7528\u4e8e\u5904\u7406BERT\u3001GPT\u3001T5\u7b49\u9884\u8bad\u7ec3\u6a21\u578b\uff0c\u652f\u6301\u8fc1\u79fb\u5b66\u4e60\u3002<\/li>\n<\/ul>\n\n\n\n

      3. \u6587\u672c\u9884\u5904\u7406\u4e0e\u6e05\u6d17<\/strong><\/h4>\n\n\n\n
        \n
      • \u5206\u8bcd<\/strong>\uff1a\u5c06\u6587\u672c\u5207\u5206\u4e3a\u5355\u72ec\u7684\u5355\u8bcd\u6216\u5b50\u8bcd\u3002<\/li>\n\n\n\n
      • \u53bb\u9664\u505c\u7528\u8bcd<\/strong>\uff1a\u5982\u201c\u7684\u201d\u3001\u201c\u4e86\u201d\u7b49\u6ca1\u6709\u5b9e\u9645\u610f\u4e49\u7684\u8bcd\u3002<\/li>\n\n\n\n
      • \u8bcd\u5e72\u63d0\u53d6\u4e0e\u8bcd\u5f62\u8fd8\u539f<\/strong>\uff1a\u4f8b\u5982\u5c06\u201crunning\u201d\u8fd8\u539f\u4e3a\u201crun\u201d\u3002<\/li>\n\n\n\n
      • \u6b63\u5219\u8868\u8fbe\u5f0f<\/strong>\uff1a\u7528\u6765\u5904\u7406\u548c\u6e05\u6d17\u6587\u672c\uff08\u5982\u53bb\u9664\u7279\u6b8a\u5b57\u7b26\u3001\u6570\u5b57\u7b49\uff09\u3002<\/li>\n<\/ul>\n\n\n\n

        \u4e8c\u3001\u6587\u672c\u8868\u793a\u65b9\u6cd5\uff1a\u5411\u91cf\u5316\u4e0e\u5d4c\u5165<\/h3>\n\n\n\n

        1. \u8bcd\u888b\u6a21\u578b\uff08Bag of Words\uff09<\/strong><\/h4>\n\n\n\n
          \n
        • \u6bcf\u4e2a\u5355\u8bcd\u90fd\u4f5c\u4e3a\u4e00\u4e2a\u7279\u5f81\uff0c\u6587\u672c\u88ab\u8f6c\u6362\u4e3a\u4e00\u4e2a\u56fa\u5b9a\u5927\u5c0f\u7684\u5411\u91cf\u3002<\/li>\n\n\n\n
        • \u4f7f\u7528CountVectorizer<\/code>\u6216TfidfVectorizer<\/code>\uff08sklearn\uff09\u6765\u5b9e\u73b0\u3002<\/li>\n<\/ul>\n\n\n\n
             from sklearn.feature_extraction.text import CountVectorizer\n\n   corpus = ['This is the first document.',\n             'This document is the second document.',\n             'And this is the third one.']\n\n   vectorizer = CountVectorizer()\n   X = vectorizer.fit_transform(corpus)\n   print(vectorizer.get_feature_names_out())  # \u6253\u5370\u8bcd\u6c47\u8868\n   print(X.toarray())  # \u6253\u5370\u8bcd\u888b\u6a21\u578b\u7684\u7a00\u758f\u77e9\u9635<\/code><\/pre>\n\n\n\n
          2. TF-IDF\uff08Term Frequency-Inverse Document Frequency\uff09<\/strong><\/h4>\n\n\n\n
            \n
          • \u7528\u4e8e\u8861\u91cf\u5355\u8bcd\u5728\u6587\u6863\u4e2d\u7684\u91cd\u8981\u6027\uff0c\u5e38\u7528\u4e8e\u6587\u672c\u5206\u7c7b\u4efb\u52a1\u3002<\/li>\n\n\n\n
          • \u4f7f\u7528TfidfVectorizer<\/code>\u8fdb\u884c\u5b9e\u73b0\u3002<\/li>\n<\/ul>\n\n\n\n
               from sklearn.feature_extraction.text import TfidfVectorizer\n\n   corpus = ['This is the first document.',\n             'This document is the second document.',\n             'And this is the third one.']\n\n   vectorizer = TfidfVectorizer()\n   X = vectorizer.fit_transform(corpus)\n   print(vectorizer.get_feature_names_out())  # \u6253\u5370\u8bcd\u6c47\u8868\n   print(X.toarray())  # \u6253\u5370TF-IDF\u77e9\u9635<\/code><\/pre>\n\n\n\n
            3. \u8bcd\u5411\u91cf\uff08Word Embeddings\uff09<\/strong><\/h4>\n\n\n\n
              \n
            • Word2Vec<\/strong>\uff1a\u901a\u8fc7\u795e\u7ecf\u7f51\u7edc\u6a21\u578b\u8bad\u7ec3\u8bcd\u5411\u91cf\u8868\u793a\uff0c\u6355\u6349\u5355\u8bcd\u4e4b\u95f4\u7684\u8bed\u4e49\u5173\u7cfb\u3002<\/li>\n\n\n\n
            • GloVe<\/strong>\uff1a\u53e6\u4e00\u79cd\u9884\u8bad\u7ec3\u7684\u8bcd\u5411\u91cf\u6a21\u578b\uff0c\u57fa\u4e8e\u77e9\u9635\u5206\u89e3\u3002<\/li>\n\n\n\n
            • \u4f7f\u7528Gensim<\/code>\u6765\u52a0\u8f7d\u548c\u4f7f\u7528Word2Vec\u6216GloVe\u6a21\u578b\u3002<\/li>\n<\/ul>\n\n\n\n
                 import gensim.downloader as api\n   model = api.load(\"glove-wiki-gigaword-100\")  # \u52a0\u8f7d\u9884\u8bad\u7ec3GloVe\u6a21\u578b\n   vector = model['computer']  # \u83b7\u53d6\"computer\"\u7684\u8bcd\u5411\u91cf<\/code><\/pre>\n\n\n\n
                \n
              • FastText<\/strong>\uff1a\u7531Facebook\u63d0\u4f9b\u7684\u8bcd\u5d4c\u5165\u6a21\u578b\uff0c\u652f\u6301\u5904\u7406\u8bcd\u6c47\u5916\u7684\u5355\u8bcd\uff08\u901a\u8fc7\u8bcd\u7d20\u8868\u793a\uff09\u3002<\/li>\n<\/ul>\n\n\n\n
                4. \u9884\u8bad\u7ec3\u8bed\u8a00\u6a21\u578b<\/strong><\/h4>\n\n\n\n
                  \n
                • BERT<\/strong>\u3001GPT-3<\/strong>\u3001T5<\/strong>\u7b49\u6a21\u578b\uff0c\u4f7f\u7528Hugging Face<\/code>\u7684Transformers<\/code>\u5e93\uff0c\u63d0\u4f9b\u4e86\u6700\u5148\u8fdb\u7684\u9884\u8bad\u7ec3\u6a21\u578b\u3002<\/li>\n<\/ul>\n\n\n\n
                     from transformers import BertTokenizer, BertForMaskedLM\n\n   # \u52a0\u8f7dBERT\u6a21\u578b\u548ctokenizer\n   tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')\n   model = BertForMaskedLM.from_pretrained('bert-base-uncased')\n\n   # \u8f93\u5165\u6587\u672c\n   text = \"Hello, my name is [MASK].\"\n   inputs = tokenizer(text, return_tensors=\"pt\")\n   outputs = model(**inputs)<\/code><\/pre>\n\n\n\n
                  \u4e09\u3001NLP\u4efb\u52a1\u5b9e\u73b0\u4e0e\u6280\u5de7<\/h3>\n\n\n\n
                  1. \u6587\u672c\u5206\u7c7b<\/strong><\/h4>\n\n\n\n
                    \n
                  • \u4f7f\u7528sklearn<\/code>\u7684LogisticRegression<\/code>\u3001SVM<\/code>\u6216\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\uff08\u5982CNN\u3001RNN\uff09\u8fdb\u884c\u6587\u672c\u5206\u7c7b\u3002<\/li>\n\n\n\n
                  • \u8bad\u7ec3\u6570\u636e\u5305\u62ec\u6587\u672c\u548c\u6807\u7b7e\uff0c\u7279\u5f81\u53ef\u4ee5\u4f7f\u7528\u8bcd\u888b\u3001TF-IDF\u6216\u8bcd\u5411\u91cf\u8868\u793a\u3002<\/li>\n<\/ul>\n\n\n\n
                       from sklearn.model_selection import train_test_split\n   from sklearn.linear_model import LogisticRegression\n   from sklearn.feature_extraction.text import TfidfVectorizer\n\n   # \u793a\u4f8b\u6570\u636e\n   corpus = ['I love programming', 'Python is awesome', 'I hate bugs']\n   labels = [1, 1, 0]  # 1\u8868\u793a\u79ef\u6781\uff0c0\u8868\u793a\u6d88\u6781\n\n   # \u6570\u636e\u9884\u5904\u7406\n   vectorizer = TfidfVectorizer()\n   X = vectorizer.fit_transform(corpus)\n   X_train, X_test, y_train, y_test = train_test_split(X, labels, test_size=0.2)\n\n   # \u8bad\u7ec3\u6a21\u578b\n   model = LogisticRegression()\n   model.fit(X_train, y_train)\n   print(f\"Accuracy: {model.score(X_test, y_test)}\")<\/code><\/pre>\n\n\n\n
                    2. \u547d\u540d\u5b9e\u4f53\u8bc6\u522b\uff08NER\uff09<\/strong><\/h4>\n\n\n\n
                      \n
                    • \u7528\u6765\u8bc6\u522b\u6587\u672c\u4e2d\u7684\u5b9e\u4f53\uff0c\u5982\u4eba\u540d\u3001\u5730\u540d\u3001\u7ec4\u7ec7\u540d\u7b49\u3002<\/li>\n\n\n\n
                    • \u4f7f\u7528spaCy<\/code>\u6216nltk<\/code>\u8fdb\u884c\u5b9e\u73b0\u3002<\/li>\n<\/ul>\n\n\n\n
                         import spacy\n\n   # \u52a0\u8f7d\u9884\u8bad\u7ec3\u6a21\u578b\n   nlp = spacy.load('en_core_web_sm')\n   doc = nlp(\"Apple is looking at buying U.K. startup for $1 billion\")\n\n   # \u6253\u5370\u547d\u540d\u5b9e\u4f53\n   for ent in doc.ents:\n       print(ent.text, ent.label_)<\/code><\/pre>\n\n\n\n
                      3. \u60c5\u611f\u5206\u6790<\/strong><\/h4>\n\n\n\n
                        \n
                      • \u4f7f\u7528TextBlob<\/code>\u3001VADER<\/code>\u3001Transformers<\/code>\u7b49\u5de5\u5177\u8fdb\u884c\u60c5\u611f\u5206\u6790\u3002<\/li>\n<\/ul>\n\n\n\n
                           from textblob import TextBlob\n\n   text = \"I love this movie!\"\n   blob = TextBlob(text)\n   print(blob.sentiment)  # \u8fd4\u56de\u60c5\u611f\u5206\u6790\u7684\u7ed3\u679c\uff08\u6781\u6027\u3001\u4e3b\u89c2\u6027\uff09<\/code><\/pre>\n\n\n\n
                        4. \u6587\u672c\u751f\u6210\u4e0e\u673a\u5668\u7ffb\u8bd1<\/strong><\/h4>\n\n\n\n
                          \n
                        • \u4f7f\u7528GPT-3<\/code>\u3001T5<\/code>\u7b49\u6a21\u578b\u8fdb\u884c\u6587\u672c\u751f\u6210\u6216\u7ffb\u8bd1\u4efb\u52a1\u3002<\/li>\n<\/ul>\n\n\n\n
                             from transformers import pipeline\n\n   # \u4f7f\u7528Hugging Face\u7684pipeline\u8fdb\u884c\u6587\u672c\u751f\u6210\n   generator = pipeline('text-generation', model='gpt-2')\n   print(generator(\"Once upon a time\"))<\/code><\/pre>\n\n\n\n
                          5. \u8bcd\u6027\u6807\u6ce8\u4e0e\u53e5\u6cd5\u5206\u6790<\/strong><\/h4>\n\n\n\n
                            \n
                          • \u4f7f\u7528spaCy<\/code>\u8fdb\u884c\u8bcd\u6027\u6807\u6ce8\u548c\u4f9d\u5b58\u53e5\u6cd5\u5206\u6790\u3002<\/li>\n<\/ul>\n\n\n\n
                               import spacy\n\n   # \u52a0\u8f7d\u6a21\u578b\n   nlp = spacy.load('en_core_web_sm')\n   doc = nlp(\"SpaCy is an NLP library.\")\n\n   # \u6253\u5370\u8bcd\u6027\u6807\u6ce8\n   for token in doc:\n       print(token.text, token.pos_)<\/code><\/pre>\n\n\n\n
                            \u56db\u3001\u5b9e\u8df5\u9879\u76ee<\/h3>\n\n\n\n
                              \n
                            1. \u60c5\u611f\u5206\u6790<\/strong><\/li>\n<\/ol>\n\n\n\n
                                \n
                              • \u4f7f\u7528IMDb\u7535\u5f71\u8bc4\u8bba\u6570\u636e\u96c6\u8fdb\u884c\u60c5\u611f\u5206\u6790\uff0c\u8bad\u7ec3\u6a21\u578b\u5e76\u8fdb\u884c\u9884\u6d4b\u3002<\/li>\n<\/ul>\n\n\n\n
                                  \n
                                1. \u6587\u672c\u5206\u7c7b<\/strong><\/li>\n<\/ol>\n\n\n\n
                                    \n
                                  • \u4f7f\u752820 Newsgroups\u6570\u636e\u96c6\uff0c\u8bad\u7ec3\u4e00\u4e2a\u6587\u672c\u5206\u7c7b\u5668\uff0c\u5206\u7c7b\u65b0\u95fb\u7ec4\u6587\u7ae0\u3002<\/li>\n<\/ul>\n\n\n\n
                                      \n
                                    1. \u804a\u5929\u673a\u5668\u4eba<\/strong><\/li>\n<\/ol>\n\n\n\n
                                        \n
                                      • \u4f7f\u7528RNN\u6216Transformer\u6a21\u578b\u6784\u5efa\u4e00\u4e2a\u7b80\u5355\u7684\u804a\u5929\u673a\u5668\u4eba\u3002<\/li>\n<\/ul>\n\n\n\n
                                          \n
                                        1. \u547d\u540d\u5b9e\u4f53\u8bc6\u522b\uff08NER\uff09<\/strong><\/li>\n<\/ol>\n\n\n\n
                                            \n
                                          • \u4f7f\u7528\u516c\u5f00\u7684\u6587\u672c\u6570\u636e\u96c6\uff08\u5982\u65b0\u95fb\u3001\u533b\u5b66\u6587\u732e\uff09\u8bad\u7ec3\u547d\u540d\u5b9e\u4f53\u8bc6\u522b\u6a21\u578b\u3002<\/li>\n<\/ul>\n\n\n\n
                                            \u603b\u7ed3<\/h3>\n\n\n\n
                                            \u901a\u8fc7\u638c\u63e1\u6587\u672c\u9884\u5904\u7406\u3001\u8bcd\u5411\u91cf\u8868\u793a\u3001\u5404\u79cdNLP\u4efb\u52a1\u548c\u5e94\u7528\u7684\u6280\u5de7\uff0c\u4f60\u5c06\u80fd\u591f\u5904\u7406\u5404\u79cd\u81ea\u7136\u8bed\u8a00\u5904\u7406\u95ee\u9898\u3002\u4ece\u57fa\u7840\u7684\u6587\u672c\u5206\u7c7b\u5230\u66f4\u9ad8\u7ea7\u7684\u751f\u6210\u4efb\u52a1\uff0cPython\u53ca\u5176\u5f3a\u5927\u7684NLP\u5e93\uff08\u5982spaCy<\/code>\u3001NLTK<\/code>\u3001Hugging Face<\/code>\u7b49\uff09\u4e3a\u4f60\u63d0\u4f9b\u4e86\u4e30\u5bcc\u7684\u5de5\u5177\u548c\u8d44\u6e90\u3002\u4e0d\u65ad\u8fdb\u884c\u9879\u76ee\u5b9e\u8df5\uff0c\u79ef\u7d2f\u7ecf\u9a8c\uff0c\u662f\u638c\u63e1NLP\u7684\u6700\u4f73\u9014\u5f84\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"
                                            \u81ea\u7136\u8bed\u8a00\u5904\u7406\uff08NLP\uff09\u662f\u8ba1\u7b97\u673a\u79d1\u5b66\u3001\u4eba\u5de5\u667a\u80fd\u548c\u8bed\u8a00\u5b66\u4ea4\u53c9\u7684\u9886\u57df\uff0c\u5b83\u4f7f\u5f97\u8ba1\u7b97\u673a\u80fd\u591f\u7406\u89e3\u3001\u5206\u6790\u3001\u751f\u6210\u548c\u4e0e\u4eba\u7c7b\u8bed\u8a00\u8fdb […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-904","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/904","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/comments?post=904"}],"version-history":[{"count":1,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/904\/revisions"}],"predecessor-version":[{"id":905,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/posts\/904\/revisions\/905"}],"wp:attachment":[{"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/media?parent=904"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/categories?post=904"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.laixuexila.com\/index.php\/wp-json\/wp\/v2\/tags?post=904"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}