BARTNER icon indicating copy to clipboard operation
BARTNER copied to clipboard

Results 18 BARTNER issues
Sort by recently updated
recently updated
newest added

请问替换为中文的fnlp/bart-large-chinese 模型后,如何改动代码,能让bart训练中文?请问有 训练成功过吗?

Hello! I'm using this model architecture to do NER on domain specific tasks and it worked pretty well! However the old version of transformer is still a little bit troublesome....

如题。 请问,论文有在中文数据集上进行实验吗?效果如何?

您好! 想咨询下,FBartDecoder类中,mapping = torch.LongTensor([0, 2]+label_ids) 其中的 0, 2 代表什么?

In Epoch:16/Step:17296, got best dev performance: Seq2SeqSpanMetric: f=0.0, rec=0.0, pre=0.0, em=0.1836 .... File "/root/work/BARTNER/model/callbacks.py", line 107, in on_valid_end raise RuntimeError("The program has been running off.") RuntimeError: The program has been...

请问,论文模型图的输出索引为什么是2 3 7 2 5 6,而不是2 3 7 2 5 7?

想问问train.py中的“如果低于0.04大概率是讯飞了”是什么意思呢 ![image](https://user-images.githubusercontent.com/73807088/170953410-6e144739-31e9-4608-8797-2b59439b9f87.png)

同学你好, 感谢你开源的代码和完整的注释。 我在conll03上复现了论文的结果,但在ontonote上遇到了一些困难。 我使用`https://github.com/yuchenlin/OntoNotes-5.0-NER-BIO`上提供的数据,并修改 https://github.com/yhcc/BARTNER/blob/d54d33127f0b8032c5ea78afcf20ef44fbccf058/train.py#L124-L126 为 ``` paths = { 'train': "/home/yedeming/data/ontonotes/onto.train.ner", 'dev': "/home/yedeming/data/ontonotes/onto.development.ner", 'test': "/home/yedeming/data/ontonotes/onto.test.ner", } ``` 运行结果如下: ``` Save cache to caches/data_facebook/bart-large_en-ontonotes_word.pt. max_len_a:0.8, max_len:10 In total 3 datasets:...

Traceback (most recent call last): File "predictor.py", line 128, in tgt_seq_len = (tgt_seq_len - 2).tolist() NameError: name 'tgt_seq_len' is not defined

fastNLP框架有点复杂,提供的predictor看着好像只能识别出conll2003格式的数据,能不能给一个通用的predictor,或者用来测试数据f值得evaluator