{"id":3308,"date":"2024-08-30T17:14:49","date_gmt":"2024-08-30T09:14:49","guid":{"rendered":"https:\/\/infernews.com\/?page_id=3308"},"modified":"2024-08-30T17:23:46","modified_gmt":"2024-08-30T09:23:46","slug":"python-%e5%af%a6%e4%bd%9c-text-embedding-%e7%9a%84%e7%b0%a1%e5%96%ae%e7%af%84%e4%be%8b","status":"publish","type":"page","link":"https:\/\/infernews.com\/blog\/python-%e5%af%a6%e4%bd%9c-text-embedding-%e7%9a%84%e7%b0%a1%e5%96%ae%e7%af%84%e4%be%8b\/","title":{"rendered":"Python \u5be6\u4f5c Text Embedding \u7684\u7c21\u55ae\u7bc4\u4f8b"},"content":{"rendered":"\n<h3 class=\"wp-block-heading\">\u4ec0\u9ebc\u662f Text Embedding\uff1f<\/h3>\n\n\n\n<p>Text Embedding \u5c07\u6587\u5b57\u8f49\u63db\u70ba\u6578\u503c\u5411\u91cf\uff0c\u8b93\u96fb\u8166\u80fd\u5920\u7406\u89e3\u548c\u8655\u7406\u6587\u5b57\u3002\u9019\u4e9b\u5411\u91cf\u6355\u6349\u4e86\u6587\u5b57\u7684\u8a9e\u7fa9\u548c\u8a9e\u6cd5\u8cc7\u8a0a\uff0c\u8b93\u6211\u5011\u53ef\u4ee5\u9032\u884c\u5404\u7a2e\u81ea\u7136\u8a9e\u8a00\u8655\u7406\u4efb\u52d9\uff0c\u4f8b\u5982\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u76f8\u4f3c\u5ea6\u8a08\u7b97:<\/strong> \u8a08\u7b97\u5169\u500b\u6587\u5b57\u4e4b\u9593\u7684\u76f8\u4f3c\u5ea6<\/li>\n\n\n\n<li><strong>\u5206\u985e:<\/strong> \u5c07\u6587\u5b57\u5206\u70ba\u4e0d\u540c\u7684\u985e\u5225<\/li>\n\n\n\n<li><strong>\u805a\u985e:<\/strong> \u5c07\u76f8\u4f3c\u7684\u6587\u5b57\u5206\u7d44<\/li>\n\n\n\n<li><strong>\u63a8\u85a6\u7cfb\u7d71:<\/strong> \u57fa\u65bc\u7528\u6236\u7684\u6b77\u53f2\u884c\u70ba\u63a8\u85a6\u76f8\u95dc\u5167\u5bb9<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\">\u4f7f\u7528 Gensim \u5eab\u5be6\u4f5c<\/h3>\n\n\n\n<p>Gensim \u662f\u4e00\u500b\u975e\u5e38\u6d41\u884c\u7684 Python \u5eab\uff0c\u5c08\u9580\u7528\u65bc\u4e3b\u984c\u5efa\u6a21\u548c\u6587\u4ef6\u76f8\u4f3c\u5ea6\u5206\u6790\u3002\u5b83\u63d0\u4f9b\u4e86\u4e00\u500b\u7c21\u55ae\u7684\u65b9\u6cd5\u4f86\u8a13\u7df4\u548c\u4f7f\u7528 word embeddings\u3002<\/p>\n\n\n\n<p>Python<\/p>\n\n\n\n<div class=\"codecopy-container\">\n                <div class=\"codecopy-header\">\n                    \n                    <button class=\"codecopy-btn\" data-target=\"codecopy-69f8c230378ea\" title=\"Copy code to clipboard\">\n                <svg width=\"16\" height=\"16\" viewBox=\"0 0 24 24\" fill=\"none\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\">\n                    <path d=\"M16 1H4C2.9 1 2 1.9 2 3V17H4V3H16V1ZM19 5H8C6.9 5 6 5.9 6 7V21C6 22.1 6.9 23 8 23H19C20.1 23 21 22.1 21 21V7C21 5.9 20.1 5 19 5ZM19 21H8V7H19V21Z\" fill=\"currentColor\"\/>\n                <\/svg>\n                <span class=\"codecopy-text\">Copy<\/span>\n            <\/button>\n                <\/div>\n                <pre class=\"line-numbers\" id=\"codecopy-69f8c230378ea\"><code class=\"language-text\">from gensim.models import Word2Vec\n\n# Sample sentences\nsentences = &#91;&#91;'\u6211', '\u559c\u6b61', '\u5403', '\u860b\u679c'],\n            &#91;'\u860b\u679c', '\u662f\u4e00\u7a2e', '\u6c34\u679c'],\n            &#91;'\u6211', '\u4e5f', '\u559c\u6b61', '\u9999\u8549']]\n\n# \u8a13\u7df4 Word2Vec \u6a21\u578b\nmodel = Word2Vec(sentences, vector_size=100, window=5, min_count=1, workers=4)\n\n# \u7372\u53d6\u4e00\u500b\u8a5e\u7684\u5411\u91cf\u8868\u793a\nprint(model.wv&#91;'\u860b\u679c'])\n\n# \u8a08\u7b97\u5169\u500b\u8a5e\u7684\u76f8\u4f3c\u5ea6\nprint(model.wv.similarity('\u860b\u679c', '\u9999\u8549'))\n\n# \u627e\u5230\u8207'\u860b\u679c'\u6700\u76f8\u4f3c\u7684\u8a5e\nprint(model.wv.most_similar('\u860b\u679c'))\n<\/code><\/pre>\n            <\/div>\n\n\n\n<h3 class=\"wp-block-heading\">\u7a0b\u5f0f\u78bc\u89e3\u8aaa<\/h3>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>\u5c0e\u5165 Gensim:<\/strong> \u9996\u5148\uff0c\u6211\u5011\u5c0e\u5165 Gensim \u5eab\u3002<\/li>\n\n\n\n<li><strong>\u6e96\u5099\u8cc7\u6599:<\/strong> \u6211\u5011\u6e96\u5099\u4e86\u4e00\u4e9b\u7c21\u55ae\u7684\u53e5\u5b50\uff0c\u4f5c\u70ba\u8a13\u7df4\u8cc7\u6599\u3002<\/li>\n\n\n\n<li><strong>\u8a13\u7df4\u6a21\u578b:<\/strong>\n<ul class=\"wp-block-list\">\n<li><code class=\"\">vector_size<\/code>: \u6bcf\u500b\u8a5e\u7684\u5411\u91cf\u7dad\u5ea6\uff0c\u53ef\u4ee5\u8abf\u6574\u3002<\/li>\n\n\n\n<li><code class=\"\">window<\/code>: \u4e0a\u4e0b\u6587\u7a97\u53e3\u5927\u5c0f\uff0c\u5373\u8003\u616e\u591a\u5c11\u500b\u5468\u570d\u8a5e\u4f86\u5b78\u7fd2\u8a5e\u5411\u91cf\u3002<\/li>\n\n\n\n<li><code class=\"\">min_count<\/code>: \u5ffd\u7565\u51fa\u73fe\u983b\u7387\u5c11\u65bc\u8a72\u503c\u7684\u8a5e\u3002<\/li>\n\n\n\n<li><code class=\"\">workers<\/code>: \u4f7f\u7528\u7684 CPU \u6838\u5fc3\u6578\u3002<\/li>\n<\/ul>\n<\/li>\n\n\n\n<li><strong>\u7372\u53d6\u8a5e\u5411\u91cf:<\/strong> \u4f7f\u7528 <code class=\"\">model.wv['\u860b\u679c']<\/code> \u53ef\u4ee5\u5f97\u5230 &#8216;\u860b\u679c&#8217; \u7684\u5411\u91cf\u8868\u793a\u3002<\/li>\n\n\n\n<li><strong>\u8a08\u7b97\u76f8\u4f3c\u5ea6:<\/strong> <code class=\"\">model.wv.similarity<\/code> \u8a08\u7b97\u5169\u500b\u8a5e\u7684\u9918\u5f26\u76f8\u4f3c\u5ea6\u3002<\/li>\n\n\n\n<li><strong>\u5c0b\u627e\u76f8\u4f3c\u8a5e:<\/strong> <code class=\"\">model.wv.most_similar<\/code> \u627e\u5230\u8207\u76ee\u6a19\u8a5e\u6700\u76f8\u4f3c\u7684\u8a5e\u3002<\/li>\n<\/ol>\n\n\n\n<h3 class=\"wp-block-heading\">\u9032\u4e00\u6b65\u63a2\u7d22<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u5176\u4ed6\u6a21\u578b:<\/strong> Gensim \u9084\u652f\u6301 GloVe\u3001FastText \u7b49\u5176\u4ed6 word embedding \u6a21\u578b\u3002<\/li>\n\n\n\n<li><strong>\u9810\u8a13\u7df4\u6a21\u578b:<\/strong> \u53ef\u4ee5\u4f7f\u7528\u9810\u8a13\u7df4\u597d\u7684 word embedding \u6a21\u578b\uff0c\u4f8b\u5982 Google \u7684 Word2Vec \u6a21\u578b\u3002<\/li>\n\n\n\n<li><strong>\u53e5\u5b50\u5411\u91cf:<\/strong> \u53ef\u4ee5\u5c0d\u6574\u500b\u53e5\u5b50\u9032\u884c\u5411\u91cf\u5316\uff0c\u4f8b\u5982\u4f7f\u7528 Doc2Vec\u3002<\/li>\n\n\n\n<li><strong>\u6df1\u5ea6\u5b78\u7fd2\u6a21\u578b:<\/strong> \u53ef\u4ee5\u4f7f\u7528\u6df1\u5ea6\u5b78\u7fd2\u6a21\u578b\uff0c\u4f8b\u5982 BERT\u3001GPT\uff0c\u4f86\u5b78\u7fd2\u66f4\u8907\u96dc\u7684\u6587\u5b57\u8868\u793a\u3002<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\">\u6ce8\u610f\u4e8b\u9805<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u8cc7\u6599\u91cf:<\/strong> \u8a13\u7df4\u4e00\u500b\u597d\u7684 word embedding \u6a21\u578b\u9700\u8981\u5927\u91cf\u7684\u6587\u672c\u8cc7\u6599\u3002<\/li>\n\n\n\n<li><strong>\u8d85\u53c3\u6578\u8abf\u512a:<\/strong> \u4e0d\u540c\u7684\u4efb\u52d9\u548c\u8cc7\u6599\u96c6\u9700\u8981\u8abf\u6574\u4e0d\u540c\u7684\u8d85\u53c3\u6578\u3002<\/li>\n\n\n\n<li><strong>\u4e2d\u6587\u8655\u7406:<\/strong> \u5c0d\u65bc\u4e2d\u6587\uff0c\u9700\u8981\u5148\u9032\u884c\u5206\u8a5e\uff0c\u7136\u5f8c\u518d\u8a13\u7df4 word embedding \u6a21\u578b\u3002<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\">\u61c9\u7528\u5834\u666f<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u641c\u5c0b\u5f15\u64ce:<\/strong> \u63d0\u9ad8\u641c\u5c0b\u7d50\u679c\u7684\u76f8\u95dc\u6027<\/li>\n\n\n\n<li><strong>\u63a8\u85a6\u7cfb\u7d71:<\/strong> \u70ba\u7528\u6236\u63a8\u85a6\u76f8\u4f3c\u7684\u7269\u54c1<\/li>\n\n\n\n<li><strong>\u804a\u5929\u6a5f\u5668\u4eba:<\/strong> \u7406\u89e3\u7528\u6236\u7684\u610f\u5716<\/li>\n\n\n\n<li><strong>\u6587\u672c\u5206\u985e:<\/strong> \u5c07\u6587\u672c\u5206\u70ba\u4e0d\u540c\u7684\u985e\u5225<\/li>\n\n\n\n<li><strong>\u60c5\u611f\u5206\u6790:<\/strong> \u5206\u6790\u6587\u672c\u7684\u60c5\u611f<\/li>\n<\/ul>\n\n\n\n<p><strong>\u9019\u500b\u4f8b\u5b50\u53ea\u662f\u5165\u9580\u7d1a\u7684\u6f14\u793a\u3002<\/strong> \u5728\u5be6\u969b\u61c9\u7528\u4e2d\uff0c\u4f60\u9700\u8981\u6839\u64da\u5177\u9ad4\u7684\u4efb\u52d9\u548c\u8cc7\u6599\u9078\u64c7\u5408\u9069\u7684\u6a21\u578b\u548c\u8d85\u53c3\u6578\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\">Gensim \u8655\u7406\u4e2d\u6587\uff1a\u4f60\u9700\u8981\u77e5\u9053\u7684\u4e8b<\/h2>\n\n\n\n<p><strong>Gensim<\/strong> \u662f\u4e00\u500b\u5f37\u5927\u7684 Python \u5eab\uff0c\u4e3b\u8981\u7528\u65bc\u4e3b\u984c\u5efa\u6a21\u548c\u6587\u4ef6\u76f8\u4f3c\u5ea6\u5206\u6790\u3002\u96d6\u7136\u5b83\u5728\u82f1\u6587\u6587\u672c\u8655\u7406\u4e0a\u8868\u73fe\u51fa\u8272\uff0c\u4f46\u8981\u8655\u7406\u4e2d\u6587\uff0c\u9084\u9700\u8981\u4e00\u4e9b\u984d\u5916\u7684\u6b65\u9a5f\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Gensim \u8655\u7406\u4e2d\u6587\u7684\u6311\u6230\u8207\u89e3\u6c7a\u65b9\u6848<\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u5206\u8a5e:<\/strong> \u4e2d\u6587\u4e0d\u50cf\u82f1\u6587\u6709\u660e\u986f\u7684\u7a7a\u683c\u5206\u9694\u55ae\u8a5e\uff0c\u56e0\u6b64\u9700\u8981\u5148\u9032\u884c\u5206\u8a5e\u3002\u5e38\u7528\u7684\u4e2d\u6587\u5206\u8a5e\u5de5\u5177\u6709 Jieba\u3001HanLP \u7b49\u3002<\/li>\n\n\n\n<li><strong>\u5b57\u5143\u7de8\u78bc:<\/strong> Gensim \u9810\u8a2d\u8655\u7406\u7684\u662f ASCII \u7de8\u78bc\uff0c\u5c0d\u65bc\u4e2d\u6587\uff0c\u4f60\u9700\u8981\u78ba\u4fdd<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>\u4ec0\u9ebc\u662f Text Embedding\uff1f Text Embedding \u5c07\u6587\u5b57\u8f49\u63db\u70ba\u6578\u503c\u5411\u91cf\uff0c\u8b93\u96fb\u8166\u80fd\u5920\u7406\u89e3\u548c\u8655\u7406\u6587\u5b57\u3002\u9019\u4e9b\u5411\u91cf\u6355\u6349\u4e86\u6587\u5b57\u7684\u8a9e\u7fa9\u548c\u8a9e\u6cd5\u8cc7\u8a0a\uff0c\u8b93\u6211\u5011\u53ef\u4ee5\u9032\u884c\u5404\u7a2e\u81ea\u7136\u8a9e\u8a00\u8655\u7406\u4efb\u52d9\uff0c\u4f8b\u5982\uff1a \u4f7f\u7528 Gensim \u5eab\u5be6\u4f5c Gensim \u662f\u4e00\u500b\u975e\u5e38\u6d41\u884c\u7684 Python \u5eab\uff0c\u5c08\u9580\u7528\u65bc\u4e3b\u984c\u5efa\u6a21\u548c\u6587\u4ef6\u76f8\u4f3c\u5ea6\u5206\u6790\u3002\u5b83\u63d0\u4f9b\u4e86\u4e00\u500b\u7c21\u55ae\u7684\u65b9\u6cd5\u4f86\u8a13\u7df4\u548c\u4f7f\u7528 word embeddings\u3002 Python \u7a0b\u5f0f\u78bc\u89e3\u8aaa \u9032\u4e00\u6b65\u63a2\u7d22 \u6ce8\u610f\u4e8b\u9805 \u61c9\u7528\u5834\u666f \u9019\u500b\u4f8b\u5b50\u53ea\u662f\u5165\u9580\u7d1a\u7684\u6f14\u793a\u3002 \u5728\u5be6\u969b\u61c9\u7528\u4e2d\uff0c\u4f60\u9700\u8981\u6839\u64da\u5177\u9ad4\u7684\u4efb\u52d9\u548c\u8cc7\u6599\u9078\u64c7\u5408\u9069\u7684\u6a21\u578b\u548c\u8d85\u53c3\u6578\u3002 Gensim \u8655\u7406\u4e2d\u6587\uff1a\u4f60\u9700\u8981\u77e5\u9053\u7684\u4e8b Gensim \u662f\u4e00\u500b\u5f37\u5927\u7684 Python \u5eab\uff0c\u4e3b\u8981\u7528\u65bc\u4e3b\u984c\u5efa\u6a21\u548c\u6587\u4ef6\u76f8\u4f3c\u5ea6\u5206\u6790\u3002\u96d6\u7136\u5b83\u5728\u82f1\u6587\u6587\u672c\u8655\u7406\u4e0a\u8868\u73fe\u51fa\u8272\uff0c\u4f46\u8981\u8655\u7406\u4e2d\u6587\uff0c\u9084\u9700\u8981\u4e00\u4e9b\u984d\u5916\u7684\u6b65\u9a5f\u3002 Gensim \u8655\u7406\u4e2d\u6587\u7684\u6311\u6230\u8207\u89e3\u6c7a\u65b9\u6848<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"googlesitekit_rrm_CAowvqSiDA:productID":"","footnotes":""},"class_list":["post-3308","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/pages\/3308","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=3308"}],"version-history":[{"count":0,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/pages\/3308\/revisions"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=3308"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}