OpenNRE

OpenNRE copied to clipboard

In `train_supervised_bert.py` : - Are we supposed to get probant results when launching this script on the different datasets you suggest (`--dataset wiki80` for example) ? - It seems like...

mttmta

更换数据集

2

您好： 最近需要用到OpenNRE，遇到一些问题。 自己已经整理了数据集，但是是原始数据 ，想要训练，需要处理成对应格式的数据。 请问，数据集该用什么标注软件处理，以及rel2id是如何提取出来的，换句话说，怎么让自己的纯文本文件，处理成能训练的数据？

Maple9360

Extract Chinese Relationships

1

How to extract Chinese relationships

qiaoxiayu

OSS License compatibility question

1

There’s possible confusion on the license of your repository when you combine other open-source code. The modules `opennre/tokenization/word_piece_tokenizer.py`, `opennre/tokenization/word_tokenizer.py`, `opennre/tokenization/basic_tokenizer.py`, and `opennre/tokenization/bert_tokenizer.py` claim their licenses as **Apache-2.0**. However, the license...

Ashley123456789

metric is not taken into account in example/train_supervised_bert.py

1

In `example/train_supervised_bert.py`, it seems that `metric` parameter is not actually passed to model on the line 131 `framework.train_model('micro_f1')`.

edloginova