Skip to content

Commit

Permalink
修复语料库下载链接 fix hankcs#1148
Browse files Browse the repository at this point in the history
  • Loading branch information
hankcs authored and huminghe committed Apr 23, 2019
1 parent 68652c3 commit 7e5b51a
Show file tree
Hide file tree
Showing 5 changed files with 5 additions and 5 deletions.
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ HanLP提供下列功能:
* 词向量训练、加载、词语相似度计算、语义运算、查询、KMeans聚类
* 文档语义相似度计算
* [语料库工具](https://github.com/hankcs/HanLP/tree/master/src/main/java/com/hankcs/hanlp/corpus)
- 部分默认模型训练自小型语料库,鼓励用户自行训练。所有模块提供[训练接口](https://github.com/hankcs/HanLP/wiki),语料可参考[98年人民日报语料库](http://hanlp.linrunsoft.com/release/corpus/pku98.zip)
- 部分默认模型训练自小型语料库,鼓励用户自行训练。所有模块提供[训练接口](https://github.com/hankcs/HanLP/wiki),语料可参考[98年人民日报语料库](http://file.hankcs.com/corpus/pku98.zip)

在提供丰富功能的同时,HanLP内部模块坚持低耦合、模型坚持惰性加载、服务坚持静态提供、词典坚持明文发布,使用非常方便。默认模型训练自全世界最大规模的中文语料库,同时自带一些语料处理工具,帮助用户训练自己的模型。

Expand Down
2 changes: 1 addition & 1 deletion src/test/java/com/hankcs/demo/DemoNewWordDiscover.java
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@
*/
public class DemoNewWordDiscover
{
static final String CORPUS_PATH = TestUtility.ensureTestData("红楼梦.txt", "http://hanlp.linrunsoft.com/release/corpus/红楼梦.zip");
static final String CORPUS_PATH = TestUtility.ensureTestData("红楼梦.txt", "http://file.hankcs.com/corpus/红楼梦.zip");

public static void main(String[] args) throws IOException
{
Expand Down
2 changes: 1 addition & 1 deletion src/test/java/com/hankcs/demo/DemoSentimentAnalysis.java
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ public class DemoSentimentAnalysis
/**
* 中文情感挖掘语料-ChnSentiCorp 谭松波
*/
public static final String CORPUS_FOLDER = TestUtility.ensureTestData("ChnSentiCorp情感分析酒店评论", "http://hanlp.linrunsoft.com/release/corpus/ChnSentiCorp.zip");
public static final String CORPUS_FOLDER = TestUtility.ensureTestData("ChnSentiCorp情感分析酒店评论", "http://file.hankcs.com/corpus/ChnSentiCorp.zip");

public static void main(String[] args) throws IOException
{
Expand Down
2 changes: 1 addition & 1 deletion src/test/java/com/hankcs/demo/DemoTextClassification.java
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ public class DemoTextClassification
/**
* 搜狗文本分类语料库5个类目,每个类目下1000篇文章,共计5000篇文章
*/
public static final String CORPUS_FOLDER = TestUtility.ensureTestData("搜狗文本分类语料库迷你版", "http://hanlp.linrunsoft.com/release/corpus/sogou-text-classification-corpus-mini.zip");
public static final String CORPUS_FOLDER = TestUtility.ensureTestData("搜狗文本分类语料库迷你版", "http://file.hankcs.com/corpus/sogou-text-classification-corpus-mini.zip");
/**
* 模型保存路径
*/
Expand Down
2 changes: 1 addition & 1 deletion src/test/java/com/hankcs/hanlp/corpus/PKU.java
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ public class PKU
public static String PKU199801_TEST = "data/test/pku98/199801-test.txt";
public static String POS_MODEL = "/pos.bin";
public static String NER_MODEL = "/ner.bin";
public static final String PKU_98 = TestUtility.ensureTestData("pku98", "http://hanlp.linrunsoft.com/release/corpus/pku98.zip");
public static final String PKU_98 = TestUtility.ensureTestData("pku98", "http://file.hankcs.com/corpus/pku98.zip");

static
{
Expand Down

0 comments on commit 7e5b51a

Please sign in to comment.