zhoujx4/NLP-Series-NewWordsMining-PTMPretraining zhoujx4/NLP-Series-NewWordsMining-PTMPretraining

  • Stars
    star
    47
  • Rank 604,252 (Top 12 %)
  • Language
    Python
  • Created about 3 years ago
  • Updated about 1 year ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
zhoujx4/NLP-Series-NewWordsMining-PTMPretraining
github

zhoujx4

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

NLP实验：新词挖掘+预训练模型继续Pre-training

More Repositories

1

NLP-Series-sentence-embeddings

NLP句子编码、句子embedding、语义相似度：BERT_avg、BERT_whitening、SBERT、SmiCSE
Python
173
star
2

NLP-Series-relation-extraction

NLP关系抽取：序列标注、层叠式指针网络、Multi-head Selection、Deep Biaffine Attention
Python
101
star
3

NLP-Series-text-cls

文本分类baseline：BERT、半监督学习UDA、对抗学习、数据增强
Jupyter Notebook
98
star
4

DuEE

百度2021年语言与智能技术竞赛多形态信息抽取赛道事件抽取部分torch版baseline
Python
72
star
5

NLP-Data-Augmentation

NLP文本增强的两种方式：同义词替换（利用word2vec词表）和回译
Python
68
star
6

DuReader-Checklist-BASELINE

百度2021年语言与智能技术竞赛机器阅读理解torch版baseline
Python
53
star
7

DuIE

百度2021年语言与智能技术竞赛多形态信息抽取赛道关系抽取部分torch版baseline
Python
48
star
8

NLP-Series-text-generation-PGN

pointer-network文本生成
Python
6
star
9

Crawls

爬虫程序汇总：Scrapy和selenium爬取房天下、3房网、选哪儿网、土流网等
HTML
4
star
10

NLP-topic_model

中文主题模型构建
Jupyter Notebook
4
star
11

NLP-Series-Unified-IE

统一信息抽取实践
Python
4
star
12

Knowledge-Graph

知识图谱案例
Python
1
star
13

Spark

用pyspark实现的一个KMeans聚类算法
Python
1
star