alic-yuan / nlp-beginner-finish Goto Github PK

View Code? Open in Web Editor NEW

1.3K 1.3K 321.0 125.49 MB

此项目完成了关于 NLP-Beginner：自然语言处理入门练习的所有任务，所有代码都经过测试,可以正常运行。

Python 100.00%

python

nlp-beginner-finish's People

Contributors

Stargazers

Watchers

Forkers

hug6 beyondz fangyangbit freeide jiamim chinabjhzc zy1996code lwppwl auxiliaryai dukedj aresbit lizequnwz idoltgy salensoft houyee mojiebuddhist weics youhebuke junfanz1 wwwanghao zouxiaoyuonly liang-8421 jiayong topdreamer virtual-emperor xyxyxwtxwt shawnmaxiao juckylv hawksilent yfyan liyi3344520 ky-xing sunnyhuma171 hbwxcw vividly xxuzijian houpanpan macroice cc1019054695 lijing8388 cclauss gyplus qianjunlang shuferhoo ly3222104 feem-vampire starjf jangkyung ax-for zhouhaner eternal1025 caoxiaoqing lcyuanjiang niu-se bqlwx111 chq seeker1943 zmskye liuboccc xrosliang bebravebecurious folgerhuang sanwan ivanchenph superzhaoyang zaoyuaner zhangxuelei86 wushowdawn snaildm pq7799 votaveruno hisylvain xza1234 jason-sunyuch tangxiaochu123230 rex-liu1027 codingmin expressgit janevril sunlizhuang vencent57712 whorace97 zhishuangr shenxinnan lxing-yy lxd789 gztangde ecnughost pythonhahaha annihilater no1keeplearning kingking888 fanmengdan langshi188 berrywrq zuohehe chenzy19 wangbq18 zjy359 ghc1996

nlp-beginner-finish's Issues

task4有bug

Traceback (most recent call last):
File "main.py", line 127, in
cn.train()
File "main.py", line 71, in train
loss = model.log_likelihood(X,y)
File "/content/drive/My Drive/fudanlp/nlp-beginner-finish-master/task4/model/LSTM_CRF.py", line 40, in log_likelihood
x = x.transpose(0,1)
IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)

能否指导一下跑不起来

873101411
感谢

task3 参考目录错误

在最新的 2020/04/29 版本中, 注意力对应邱老师的<<神经网络和深度学习>>第 8 章

基于LSTM+CRF的序列标注的模型保存

你好，请问NER任务的模型保存没有按照指标保存最好的一轮吧？

生成语句的问题

大佬你好，我想问一下你使用过邱老师提供的那个数据集吗？我使用那个数据集后，随机生成句子的时候总是生成像这种字符，请问你能给我提供一点点建议吗，非常感谢。

torchcrf 是大佬自己写的吗

task5困惑度计算

想问一下task5中的perplexity困惑度该如何计算啊？好像没看到代码里有这方面的计算

Small mistake in task 2

Though it may be not worth mentioning... Just for reminder, if anyone wants to run task2, just modify the line 81 in torch_train.py and DELETE THE WORD "OPTIMIZER".

task2中评估似乎有问题吧

在task2中是不是对模型更新了，不应该将loss反向传播回去吧。如果传输回去，评估时得到的loss是已经使用了评估数据训练过的模型。

task 3 p_mask h_mask 定义错误

local inference

p_mask, h_mask = (p != 1).long(), (h != 1).long() # TODO: 这里是不是写错了 p != 0
m_p, m_h = self.inference(p_, h_, p_mask, h_mask) # m_p = m_h = [256,50,2400]

p_mask, h_mask = (p != 0).long(), (h != 0).long() 因为填充值默认是0

Asthestarfall

task1 predict.py是否有问题啊谢谢

运行环境

楼主，可否把你的运行环境展示出来，方便运行代码的时候配置相应的环境