Jie Yang

这个很奇怪也很有意思，根据log, 应该是这句在256/512/2014时有问题 `last_partition = torch.gather(partition_history, 1, last_position).view(batch_size,tag_size,1)` 不过我没时间仔细研究了，我把issue 放这，有兴趣的人可以瞅瞅。 实际使用的话，你把MAX_SENTENCE_LENGTH设置成其他值就行了。

还有，你得看看你的Python 和PyTorch 的版本。

可能需要检查一下数据格式

Thanks for this suggestion. We are working on a new version that will supports various model formats.

Hi @jd-coderepos I implemented a dev version that integrated the initial BERT model, but I didn't get enough time to finetune it. But the good news it that my student...

Good question. I planned to incorporate those various pretrained embeddings half a year ago but couldn't find enough time to implement it. I am not sure when can I release...

@CHENPoHeng Hi , we have implemented an initial version of integrating different BERT (using hugging face) in the dev version. But we haven't evaluated it. We plan to have a...

> annotate selection did not work for RTL language . how can i fix that? Sorry for the late reply. I am not sure if this bug exists, I didn't...

Hi @cosmozhang , I have implemented both Lample and Xuezhe Ma's structure using PyTorch [PyTorchSeqLabel](https://github.com/jiesutd/PyTorchSeqLabel) . The results are comparable with both of them, all the results are listed and...

Hello everyon, I know it is too late but we have update NCRF++ to YATO(https://github.com/jiesutd/YATO) which can fully utilize large pretrained language models.