WaNePr

Thanks for the'hard method', when will you relase the soft version ?

7

Thanks for the'hard method', when will you relase the soft version ?

作者你好，感谢分享。 请问在这个问题中，你考虑到KBQA的实体链指的问题了吗？

再次predict的时候f1 为0； 训练加测试时候f1有值，但是重新predict时候f1显示为0

5

我的是do_train, do_eval, do_predict同时为true的时候的f1正常； 训练结束后想再做predict则f1为0. 我的命令行如下: bert-base-ner-train --do_train=False --do_eval=False --do_predict=True --data_dir=data1/ --predict_batch_siz=16 --max_seq_length=128 --output_dir=result/ --data_config_path=result.config --vocal_file=chinese_L-12_H-768_A-12/vocab.txt --bert_config_file=chinese_L-12_H-768_A-12/bert_config.json 应该是遇到了和这边类似的问题 https://github.com/macanv/BERT-BiLSTM-CRF-NER/issues/23 求解答！

Something wrong with the total number of entities being evaluated ?

2

For msra dataset, I realised that the total number of entities being evaluated is not the same as it is. As you can see, For test data, the support (true...

如标题，求问线下的dev数据集结果和线上test的结果是否具有一致性？如果有不一致，大概差距在多少？

Do you have any idea on why attention-based model worse than the rnn model ?

5

Hi, I see that the attention-based model performs worse than the rnn-based model in the original paper. Do you have an idea why ? I also read "SPEECH EMOTION RECOGNITION...

Why no sparql for each question ?

23

Thanks for the dataset, but why there is no sparql query for each question ?

phantomjs fetcher running on port 25555 [I 190327 15:59:39 result_worker:49] result_worker starting... [I 190327 15:59:39 processor:211] processor starting... Process Process-4: Traceback (most recent call last): File "/Users/Zixuan/anaconda3/envs/py35tf/lib/python3.5/multiprocessing/process.py", line 252, in...