Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
|
|
6 years ago | |
|---|---|---|
| .. | ||
| README.md | 6 years ago | |
| load_data.py | 6 years ago | |
| main.py | 6 years ago | |
| models.py | 6 years ago | |
| modules.py | 6 years ago | |
| pathes.py | 6 years ago | |
| small.py | 6 years ago | |
| utils.py | 6 years ago | |
| utils_.py | 6 years ago | |
未包含的数据集可以通过提供增加类似 load_data.py 中 load_ontonotes4ner 这个输出格式的函数来增加对其的支持
| 数据集 | 目前达到的F1分数(test) | 原文中的F1分数(test) |
|---|---|---|
| 58.66 | 58.79 | |
| Resume | 95.18 | 94.46 |
| Ontonote | 73.62 | 73.88 |
备注:Weibo数据集我用的是V2版本,也就是更新过的版本,根据杨杰博士Github上LatticeLSTM仓库里的某个issue,应该是一致的。
to those unincluded dataset, you can write the interface function whose output form is like load_ontonotes4ner in load_data.py
| Dataset | F1 of my code(test) | F1 in paper(test) |
|---|---|---|
| 58.66 | 58.79 | |
| Resume | 95.18 | 94.46 |
| Ontonote | 73.62 | 73.88 |
PS:The Weibo dataset I use is V2, namely revised version.
一款轻量级的自然语言处理(NLP)工具包,目标是减少用户项目中的工程型代码,例如数据处理循环、训练循环、多卡运行等
Python Jupyter Notebook Text CSV Markdown