Skip to content

Commit 2401edb

Browse files
增加了 多语言词向量、文本生成、英文脏话大全 等资源
1 parent 7494d44 commit 2401edb

File tree

1 file changed

+12
-0
lines changed

1 file changed

+12
-0
lines changed

README.md

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -975,7 +975,19 @@ for word in misspelled:
975975
**249\. 中文 预训练 ELECTREA 模型: 基于对抗学习 pretrain Chinese Model** [github](https://github.com/CLUEbenchmark/ELECTRA)
976976

977977

978+
**250\. albert-chinese-ner - 用预训练语言模型ALBERT做中文NER** [github](https://github.com/ProHiryu/albert-chinese-ner)
978979

980+
**251\. 基于GPT2的特定主题文本生成/文本增广** [github](https://github.com/prakhar21/TextAugmentation-GPT2)
981+
982+
**252\. 开源预训练语言模型合集** [github](https://github.com/ZhuiyiTechnology/pretrained-models)
983+
984+
**253\. 多语言句向量包** [github](https://github.com/yannvgn/laserembeddings)
985+
986+
**254\. 编码、标记和实现:一种可控高效的文本生成方法** [github](https://github.com/yannvgn/laserembeddings)
987+
988+
**255\. 英文脏话大列表** [github](https://github.com/zacanger/profane-words)
989+
990+
**256\. attnvis:GPT2、BERT等transformer语言模型注意力交互可视化** [github](https://github.com/SIDN-IAP/attnvis)
979991

980992

981993

0 commit comments

Comments
 (0)