Update PULL_REQUEST_TEMPLATE.md

Author: FengZiYjun

Diff for: .github/PULL_REQUEST_TEMPLATE.md

@@ -2,16 +2,23 @@ Description：简要描述这次PR的内容
 
 Main reason: 做出这次修改的原因
 
+
 Checklist  检查下面各项是否完成
 
 Please feel free to remove inapplicable items for your PR.
 
--	[ ] The PR title starts with [$CATEGORY] (such as [Models], [Modules], [Core], [io], [Doc], 分别对应各个子模块)
--	[ ] Changes are complete (i.e. I finished coding on this PR)  代码写完了
--	[ ] All changes have test coverage  修改的地方经过测试。对于可复用部分的修改，例如core/和modules/，测试代码必须提供。其他部分建议提供。
--	[ ] Code is well-documented  注释写好，文档会从注释中自动抽取
--	[ ] To the my best knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change  这种情况请找核心开发人员
+-	[ ] The PR title starts with [$CATEGORY] (例如[bugfix]修复bug，[new]添加新功能，[test]修改测试，[rm]删除旧代码)
+-	[ ] Changes are complete (i.e. I finished coding on this PR)  修改完成才提PR
+-	[ ] All changes have test coverage  修改的部分顺利通过测试。对于fastnlp/fastnlp/*的修改，测试代码**必须**提供在fastnlp/test/*。
+-	[ ] Code is well-documented  注释写好，API文档会从注释中抽取
+-	[ ] To the my best knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change  修改导致例子或tutorial有变化，请找核心开发人员
 
 Changes: 逐项描述修改的内容
--	Switch to sparse_coo_matrix for torch v1.0. #282
-- Fix bug that nx graph to dgl graph is not properly converted. #286
+- 添加了新模型；用于句子分类的CNN，来自Yoon Kim的Convolutional Neural Networks for Sentence Classification
+- 修改dataset.py中过时的和不合规则的注释 #286
+- 添加对var-LSTM的测试代码
+
+Mention: 找人review你的PR
+
+@修改过这个文件的人
+@核心开发人员