{"id":9467,"date":"2025-11-07T13:58:18","date_gmt":"2025-11-07T05:58:18","guid":{"rendered":"\/?p=9467"},"modified":"2025-11-07T13:58:18","modified_gmt":"2025-11-07T05:58:18","slug":"hanlp-%e5%9f%ba%e4%ba%8e%e6%9c%b4%e7%b4%a0%e8%b4%9d%e5%8f%b6%e6%96%af-%e8%ae%ad%e7%bb%83-%e6%96%87%e6%9c%ac%e5%88%86%e7%b1%bb","status":"publish","type":"post","link":"\/?p=9467","title":{"rendered":"HanLP \u57fa\u4e8e\u6734\u7d20\u8d1d\u53f6\u65af \u8bad\u7ec3 \u6587\u672c\u5206\u7c7b"},"content":{"rendered":"

\u4e00\u3001HanLP \u6734\u7d20\u8d1d\u53f6\u65af\u5206\u7c7b\u5668<\/h2>\n

HanLP<\/code> \u9488\u5bf9\u6587\u672c\u5206\u7c7b\u7b97\u6cd5\u5df2\u7ecf\u5e2e\u6211\u4eec\u5b9e\u73b0 \u6734\u7d20\u8d1d\u53f6\u65af\u6cd5 \uff0c\u7528\u6237\u53ef\u4ee5\u65e0\u9700\u5173\u5fc3\u5185\u90e8\u7ec6\u8282\uff0cHanLP<\/code> \u4e5f\u63d0\u4f9b\u4e86\u76f8\u5173\u81ea\u5b9a\u4e49\u8bad\u7ec3\u63a5\u53e3\uff0c\u524d\u63d0\u9700\u8981\u5c06\u6570\u636e\u96c6\u6839\u636e\u5206\u7c7b\u653e\u5230\u4e0d\u540c\u7684\u76ee\u5f55\u4e2d\uff0c\u4f8b\u5982\uff1a<\/p>\n

\"\u56fe\u7247\"<\/p>\n

\u5b98\u65b9\u7ed9\u51fa\u4e86\u76f8\u5173\u6027\u80fd\u6307\u6807\u5982\u4e0b\u8868\u6240\u793a\uff0c\u5176\u4e2d SVM<\/code> \u5728\u672c\u4e13\u680f\u4e0b\u7bc7\u6587\u7ae0\u8fdb\u884c\u6f14\u793a\uff1a<\/p>\n

\"\u56fe\u7247\"<\/p>\n

\u6709\u5173\u4e8e HanLP \u73af\u5883\u7684\u642d\u5efa\uff0c\u53ef\u4ee5\u53c2\u8003\u4e0b\u9762\u8fd9\u7bc7\u6587\u7ae0\uff1a<\/p>\n

\n

https:\/\/xiaobichao.blog.csdn.net\/article\/details\/128271909<\/a><\/p>\n<\/blockquote>\n

\u51c6\u5907\u8bed\u6599\u5e93<\/h3>\n

\u4e0b\u9762\u901a\u8fc7\u4f7f\u7528 HanLP<\/code> \u57fa\u4e8e\u6734\u7d20\u8d1d\u53f6\u65af\u7b97\u6cd5\uff0c\u5b9e\u73b0\u6587\u672c\u5206\u7c7b\uff0c\u8bed\u6599\u5e93\u91c7\u7528\u641c\u72d7\u6587\u672c\u5206\u7c7b\u8bed\u6599\u5e93\u8ff7\u4f60\u7248<\/code>\u6d4b\u8bd5\u6570\u636e\u96c6\uff0c\u4e0b\u8f7d\u6570\u636e\u96c6\uff1a<\/p>\n

\n

http:\/\/file.hankcs.com\/corpus\/sogou-text-classification-corpus-mini.zip<\/a><\/p>\n<\/blockquote>\n

\u4e0b\u8f7d\u52a0\u538b\u540e\u53ef\u4ee5\u53d1\u73b0\u8be5\u6570\u636e\u96c6\u5df2\u7ecf\u6807\u6ce8\u597d\uff1a<\/p>\n

\"\u56fe\u7247\"<\/p>\n

\u6587\u672c\u6837\u4f8b\uff1a<\/p>\n

\"\u56fe\u7247\"<\/p>\n

\u8bad\u7ec3\u6570\u636e<\/h3>\n
public class ClassifyTrain {\n\n    public static void main(String[] args) throws IOException {\n        \/\/\u8bed\u6599\u5e93\u7684\u5730\u5740\n        String dataPath = "F:\/bigdata\/hanlp\/sogou-text-classification-corpus-mini\/\u641c\u72d7\u6587\u672c\u5206\u7c7b\u8bed\u6599\u5e93\u8ff7\u4f60\u7248";\n        \/\/\u6a21\u578b\u4fdd\u5b58\u8def\u5f84\n        String modelPath = "F:\/bigdata\/hanlp\/sogou-text-classification-corpus-mini\/classification-model.ser";\n        \/\/\u8bad\u7ec3\u6570\u636e\n        trainData(dataPath, modelPath);\n    }\n\n    private static void trainData(String dataPath, String modelPath) throws IOException {\n        File corpusFolder = new File(dataPath);\n        if (!corpusFolder.exists() || !corpusFolder.isDirectory())  {\n            System.err.println("\u6ca1\u6709\u6587\u672c\u5206\u7c7b\u8bed\u6599");\n            return;\n        }\n        \/\/ FileDataSet\u7701\u5185\u5b58\uff0c\u53ef\u52a0\u8f7d\u5927\u89c4\u6a21\u6570\u636e\u96c6\uff0c\u652f\u6301\u4e0d\u540c\u7684ITokenizer\uff0c\u8be6\u89c1\u6e90\u7801\u4e2d\u7684\u6587\u6863\n        \/\/ \u4f7f\u7528\u524d90% \u7684\u6570\u636e\u4f5c\u4e3a\u8bad\u7ec3\u96c6\n        IDataSet trainingCorpus = new FileDataSet()\n                .setTokenizer(new HanLPTokenizer())\n                .load(dataPath, "UTF-8", 0.9);\n        \/\/ \u521b\u5efa\u6734\u7d20\u8d1d\u53f6\u65af\u5206\u7c7b\u5668\n        IClassifier classifier = new NaiveBayesClassifier();\n        \/\/ \u8bad\u7ec3\u6570\u636e\n        classifier.train(trainingCorpus);\n        \/\/ \u83b7\u53d6\u8bad\u7ec3\u6a21\u578b\n        AbstractModel model = classifier.getModel();\n        \/\/ \u4f7f\u7528\u540e10% \u7684\u6570\u636e\u4f5c\u4e3a\u6d4b\u8bd5\u96c6\n        IDataSet testingCorpus = new MemoryDataSet(model)\n                .load(dataPath, "UTF-8", -0.1);\n        \/\/ \u8ba1\u7b97\u51c6\u786e\u7387\n        FMeasure result = Evaluator.evaluate(classifier, testingCorpus);\n        System.out.println("\u6d4b\u8bd5\u96c6\u51c6\u786e\u5ea6\uff1a");\n        System.out.println(result);\n        \/\/ \u4fdd\u5b58\u6a21\u578b\n        IOUtil.saveObjectTo(model, modelPath);\n    }\n\n}<\/code><\/pre>\n
\u67e5\u770b\u8bad\u7ec3\u65e5\u5fd7\uff1a<\/p>\n
\"\u56fe\u7247\"<\/p>\n
\u67e5\u770b\u8bad\u7ec3\u6a21\u578b\uff1a<\/p>\n
\"\u56fe\u7247\"<\/p>\n
\u6d4b\u8bd5\u6a21\u578b<\/h3>\n
public class TestClassify {\n\n    public static void main(String[] args) {\n        String modelPath = "F:\/bigdata\/hanlp\/sogou-text-classification-corpus-mini\/classification-model.ser";\n        testModel(modelPath);\n    }\n\n    private static void testModel(String modelPath){\n        NaiveBayesModel model = (NaiveBayesModel) IOUtil.readObjectFrom(modelPath);\n        IClassifier classifier = new NaiveBayesClassifier(model);\n        \/\/ \u6d4b\u8bd5\u5206\u7c7b\n        String text1 = "\u7814\u7a76\u751f\u8003\u5f55\u6a21\u5f0f\u4e9f\u5f85\u8fdb\u4e00\u6b65\u4e13\u4e1a\u5316";\n        System.out.printf("\u300a%s\u300b \u5c5e\u4e8e\u5206\u7c7b \u3010%s\u3011\\n", text1, classifier.classify(text1));\n\n        String text2 = "C\u7f57\u83b72018\u73af\u7403\u8db3\u7403\u5956\u6700\u4f73\u7403\u5458 \u5fb7\u5c1a\u8363\u81ba\u6700\u4f73\u6559\u7ec3";\n        System.out.printf("\u300a%s\u300b \u5c5e\u4e8e\u5206\u7c7b \u3010%s\u3011\\n", text2, classifier.classify(text2));\n\n        String text3 = "\u82f1\u56fd\u9020\u822a\u6bcd\u8017\u65f68\u5e74\u4ecd\u672a\u670d\u5f79 \u88ab\u4e2d\u56fd\u901f\u5ea6\u8fdc\u8fdc\u7529\u5728\u8eab\u540e";\n        System.out.printf("\u300a%s\u300b \u5c5e\u4e8e\u5206\u7c7b \u3010%s\u3011\\n", text3, classifier.classify(text3));\n\n        String text4 = "\u5982\u679c\u771f\u60f3\u7528\u98df\u7269\u89e3\u538b,\u5efa\u8bae\u53ef\u4ee5\u98df\u7528\u71d5\u9ea6";\n        System.out.printf("\u300a%s\u300b \u5c5e\u4e8e\u5206\u7c7b \u3010%s\u3011\\n", text4, classifier.classify(text4));\n\n    }\n\n}<\/code><\/pre>\n
\u6d4b\u8bd5\u7ed3\u679c\uff1a<\/p>\n
\"\u56fe\u7247\"<\/p>\n","protected":false},"excerpt":{"rendered":"
\u4e00\u3001HanLP \u6734\u7d20\u8d1d\u53f6\u65af\u5206\u7c7b\u5668 HanLP \u9488\u5bf9\u6587\u672c\u5206\u7c7b\u7b97\u6cd5\u5df2\u7ecf\u5e2e\u6211\u4eec\u5b9e\u73b0 \u6734\u7d20\u8d1d\u53f6\u65af\u6cd5 \uff0c\u7528\u6237\u53ef\u4ee5\u65e0\u9700\u5173\u5fc3\u5185\u90e8\u7ec6\u8282\uff0cHanLP \u4e5f\u63d0   \u2026 …<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ngg_post_thumbnail":0},"categories":[225],"tags":[],"_links":{"self":[{"href":"\/index.php?rest_route=\/wp\/v2\/posts\/9467"}],"collection":[{"href":"\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=9467"}],"version-history":[{"count":1,"href":"\/index.php?rest_route=\/wp\/v2\/posts\/9467\/revisions"}],"predecessor-version":[{"id":9468,"href":"\/index.php?rest_route=\/wp\/v2\/posts\/9467\/revisions\/9468"}],"wp:attachment":[{"href":"\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=9467"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=9467"},{"taxonomy":"post_tag","embeddable":true,"href":"\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=9467"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}