{"id":936,"date":"2018-05-09T11:36:28","date_gmt":"2018-05-09T03:36:28","guid":{"rendered":"http:\/\/www.rain1024.com\/?p=936"},"modified":"2023-08-07T20:57:26","modified_gmt":"2023-08-07T12:57:26","slug":"article118","status":"publish","type":"post","link":"http:\/\/rain1024.com\/index.php\/2018\/05\/09\/article118\/","title":{"rendered":"\u5173\u4e8e\u81ea\u7136\u8bed\u8a00\u5904\u7406\u5b66\u4e60"},"content":{"rendered":"<h1>\u81ea\u7136\u8bed\u8a00\u5904\u7406\u5b66\u4e60<\/h1>\n<h3>\u81ea\u7136\u8bed\u8a00\u5904\u7406\u662f\u8ba1\u7b97\u673a\u79d1\u5b66\u9886\u57df\u4e0e\u4eba\u5de5\u667a\u80fd\u9886\u57df\u7684\u4e2d\u7684\u4e00\u4e2a\u91cd\u8981\u65b9\u5411\u3002\u5b83\u7814\u7a76\u5b9e\u73b0\u4eba\u4e0e\u8ba1\u7b97\u673a\u4e4b\u95f4\u7528\u81ea\u7136\u8bed\u8a00\u8fdb\u884c\u6709\u6548\u901a\u4fe1\u7684\u5404\u79cd\u7406\u8bba\u548c\u65b9\u6cd5\uff0c\u6d89\u53ca\u6240\u6709\u7528\u8ba1\u7b97\u673a\u5bf9\u81ea\u7136\u8bed\u8a00\u8fdb\u884c\u7684\u64cd\u4f5c<\/h3>\n<h3>\u57fa\u4e8e\u300apython\u81ea\u7136\u8bed\u8a00\u5904\u7406\u300b\u4e00\u4e66\u7684\u5b66\u4e60\u8fc7\u7a0b\u5206\u4eab\uff0c\u6211\u60f3\u66f4\u7cbe\u7b80\u7684\u63d0\u53d6\u51fa\u4e66\u4e2d\u6709\u7528\u7684\u4e1c\u897f\uff0c\u4f7f\u5176\u80fd\u5feb\u901f\u4e0a\u624b\u4f7f\u7528\u3002\u7279\u6b64\u653e\u5230GitHub\u4e0a\u4e0d\u65ad\u66f4\u65b0\u3002<\/h3>\n<h3>\u6309\u7167\u4e66\u4e2d\u7684\u987a\u5e8f<\/h3>\n<h3>1. \u8bed\u8a00\u5904\u7406\u7684\u57fa\u7840<\/h3>\n<h3>2. \u7ed3\u6784\u5316\u7a0b\u5e8f\u8bbe\u8ba1<\/h3>\n<h3>3. \u8bed\u8a00\u5904\u7406\u7684\u57fa\u672c\u539f\u7406\uff08\u6807\u6ce8\uff0c\u5206\u7c7b\uff0c\u63d0\u53d6\uff09<\/h3>\n<h3>4. \u53e5\u5b50\u89e3\u6790\uff0c\u53e5\u6cd5\u7ed3\u6784\u8bc6\u522b\uff0c\u53e5\u610f\u8868\u8fbe\u65b9\u6cd5<\/h3>\n<h3>\u6240\u8c13\u201c\u81ea\u7136\u8bed\u8a00\u201d\uff0c\u662f\u6307\u4eba\u4eec\u65e5\u5e38\u4ea4\u6d41\u4f7f\u7528\u7684\u8bed\u8a00\u3002\u76f8\u5bf9\u4e8e\u7f16\u7a0b\u8bed\u8a00\u548c\u6570\u5b66\u7b26\u53f7\u8fd9\u6837\u7684\u4eba\u5de5\u8bed\u8a00\u81ea\u7136\u8bed\u8a00\u968f\u7740\u4e00\u4ee3\u4ee3\u7684\u4f20\u9012\u800c\u4e0d\u65ad\u6f14\u5316\u56e0\u800c\u5f88\u96be\u7528\u660e\u786e\u7684\u89c4\u5219\u6765\u786e\u5b9a\u3002\u4ece\u5e7f\u4e49\u4e0a\u8bb2\uff0c\u201c\u81ea\u7136\u8bed\u8a00\u5904\u7406\uff08 Natural Language Processing\uff0cNLP\uff09\u5305\u542b\u6240\u6709\u7528\u8ba1\u7b97\u673a\u5bf9\u81ea\u7136\u8bed\u8a00\u8fdb\u884c\u7684\u64cd\u4f5c\uff0c\u4ece\u6700\u7b80\u5355\u7684\u901a\u8fc7\u8ba1\u8bcd\u6c47\u51fa\u73b0\u7684\u9891\u7387\u6765\u6bd4\u8f83\u4e0d\u540c\u7684\u5199\u4f5c\u98ce\u683c\u5230\u6700\u590d\u6742\u7684\u5b8c\u5168\u201c\u7406\u89e3\u201d\u4eba\u6240\u8bf4\u7684\u8bdd\uff0c\u6216\u81f3\u5c11\u8fbe\u5230\u80fd\u5bf9\u4eba\u7684\u8bdd\u8bed\u4f5c\u51fa\u6709\u6548\u53cd\u5e94\u7684\u7a0b\u5ea6\uff0cNLP\u7684\u6280\u672f\u5e94\u7528\u65e5\u76ca\u5e7f\u6cdb\u3002\u4f8b\u5982:\u624b\u673a\u548c\u624b\u6301\u7535\u8111\u5bf9\u8f93\u5165\u6cd5\u8054\u60f3\u63d0\u793a\u548c\u624b\u5199\u8bc6\u522b\u7684\u652f\u6301:\u7f51\u7edc\u641c\u7d22\u5f15\u64ce\u80fd\u641c\u7d22\u5230\u975e\u7ed3\u6784\u5316\u6587\u672c\u4e2d\u7684\u4fe1\u606f:\u673a\u5668\u7ffb\u8bd1\u80fd\u628a\u4e2d\u6587\u6587\u672c\u7ffb\u8bd1\u6210\u897f\u73ed\u7259\u6587\u3002\u5728\u5e94\u7528\u9886\u57df\uff0c\u5305\u62ec\u4ece\u4e8b\u4eba\u673a\u4ea4\u4e92\u3001\u5546\u4e1a\u4fe1\u606f\u5206\u6790\u3001Web\u8f6f\u4ef6\u5f00\u53d1\u3002<\/h3>\n<h3>\u6559\u7a0b\u57fa\u4e8e Python\u7f16\u7a0b\u8bed\u8a00\u53ca\u540d\u4e3a\u81ea\u7136\u8bed\u8a00\u5de5\u5177\u5305\uff08 Natural Language ToolkitNLTK\uff09\u7684\u5f00\u6e90\u5e93\u3002<\/h3>\n<h2>\u5173\u4e8e\u6211\u5bf9\u81ea\u7136\u8bed\u8a00\u4e86\u89e3\uff0c\u5176\u5b9e\u4ee5\u524d\u4e0d\u6e05\u695a\u8fd9\u4e2a\u65b9\u5411\uff0c\u662f\u5728\u627e\u4e86\u5b66\u6821\u7684\u5bfc\u5e08\u540e\u624d\u77e5\u9053\u6709\u8fd9\u6837\u4e00\u4e2a\u65b9\u5411\uff0c\u548c\u5927\u591a\u6570\u4eba\u4e00\u6837\u4e00\u5f00\u59cb\u4e0d\u6e05\u695a\u81ea\u7136\u8bed\u8a00\u4ee3\u6307\u4ec0\u4e48\uff0c\u5982\u4f55\u5904\u7406\uff0c\u5b83\u7684\u8fd0\u7528\u573a\u666f\u5728\u54ea\u91cc\uff0c\u540e\u6765\u5728\u767e\u5ea6\u4e91\u91cc\u770b\u5230\u81ea\u7136\u8bed\u8a00\u5904\u7406\u63a5\u53e3\uff0c\u5305\u62ec\u57fa\u7840\u5199\u7684\u60c5\u611f\u5206\u6790\uff0c\u6587\u7ae0\u5206\u7c7b\uff0c\u5230\u4e2d\u6587\u8bcd\u5411\u91cf\uff0cCNN\u6a21\u578b\u5efa\u7acb\uff0c\u66f4\u611f\u53d7\u5230\u8fd9\u95e8\u5b66\u79d1\u7684\u5e9e\u5927\u3002\u540e\u6765\u4e00\u76f4\u5728\u548c\u8001\u5e08\u505a\u8499\u53e4\u6587\u7684\u81ea\u7136\u8bed\u8a00\u5904\u7406\uff0c\u63a5\u89e6\u4e00\u4e9b\u76ae\u6bdb\uff0c\u5e76\u672a\u6df1\u5165\u7684\u5b66\u4e60\u3002\u6700\u8fd1\u770b\u5230\u300apython\u81ea\u7136\u8bed\u8a00\u5904\u7406\u300b\u8fd9\u672c\u4e66\u6709\u4e86\u5174\u8da3\uff0c\u60f3\u770b\u4e00\u904d\uff0c\u5bf9\u5176\u80fd\u6709\u6240\u4e86\u89e3\uff0c\u4f1a\u7b80\u5355\u7684\u8fd0\u7528\u4e00\u4e9b\u3002<\/h2>\n","protected":false},"excerpt":{"rendered":"<p>\u81ea\u7136\u8bed\u8a00\u5904\u7406\u5b66\u4e60 \u81ea\u7136\u8bed\u8a00\u5904\u7406\u662f\u8ba1\u7b97\u673a\u79d1\u5b66\u9886\u57df\u4e0e\u4eba\u5de5\u667a\u80fd\u9886\u57df\u7684\u4e2d\u7684\u4e00\u4e2a\u91cd\u8981\u65b9\u5411\u3002\u5b83\u7814\u7a76\u5b9e\u73b0\u4eba\u4e0e\u8ba1\u7b97\u673a\u4e4b\u95f4\u7528\u81ea\u7136\u2026 <span class=\"read-more\"><a href=\"http:\/\/rain1024.com\/index.php\/2018\/05\/09\/article118\/\">Read More &raquo;<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[15,18],"tags":[58,89],"class_list":["post-936","post","type-post","status-publish","format-standard","hentry","category-python","category-technique","tag-python","tag-89"],"_links":{"self":[{"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/posts\/936","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/comments?post=936"}],"version-history":[{"count":1,"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/posts\/936\/revisions"}],"predecessor-version":[{"id":1415,"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/posts\/936\/revisions\/1415"}],"wp:attachment":[{"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/media?parent=936"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/categories?post=936"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/rain1024.com\/index.php\/wp-json\/wp\/v2\/tags?post=936"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}