Giter Site home page Giter Site logo

mrc4ere_plus's People

Contributors

tanyazhao avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

mrc4ere_plus's Issues

Where is the model?

Hi, thanks for providing your code, but do you forget to release the model part of your code? I can't find the BertTagger from your code. Would you please do me a favour to release your remain code?

question about your code

thanks for sharing! but one quesiton about your code mrc_utils.py
image

your labels is only consider doc tokens not conside question? this may be wrong??

求模型文件

学姐你好,最近读了您的论文发现其中**很不错。想继续深入拜读一下您的代码,但是在运行的时候发现没有模型文件,请问可以发布一下吗?或者如果您方便的话私发至我的邮箱[email protected],期待学姐的回复,感谢!祝您科研工作顺利!

No such file or directory: '../log/output_results/entity_vote_best_q.output'

Traceback (most recent call last):
File "run_tagger.py", line 360, in
main()
File "run_tagger.py", line 356, in main
train(tokenizer, model, optimizer, train_loader, dev_loader, test_loader, config, device, n_gpu, label_list, num_train_steps)
File "run_tagger.py", line 184, in train
label_list, "test", tokenizer, ent_weight, rel_weight)
File "run_tagger.py", line 241, in eval_checkpoint
with open(entity_result_file, "w") as fw:
FileNotFoundError: [Errno 2] No such file or directory: '../log/output_results/entity_vote_best_q.output'

Hi, thanks for providing your code, but do you forget to release '../log/output_results/entity_vote_best_q.output' of your code? I can't find it from your code. Would you please do me a favour to release your remain code? Thank you!

关于relation prediction模块的实现

关于论文中提到的relation prediction模块,我在代码中似乎没有找到对应的部分。
我注意到代码中在BertTagger类中,仅进行了标签的分类,在测试的时候似乎是基于entity_relation_map词典进行关系query的构建。
所以想请教一下代码中对于relation prediction是如何实现的?是不是我没找到对应的代码~

报错:generate_relation_examples

当运行到generate_relation_examples时,它会报错KeyError,entity_type not in entity_relation_map,它将关系类型误识别为实体。

Concern about the replicative process

Following what you mention in the original paper, I found that you need some hidden layers to detect relation candidates. But in your public code, I can not find any piece of code related to it. Your code and prepared dataset are all about the MRC module (or Tagger as you named it). Can you show me that part of your proposal?
PS. Like others mentioned, I also can not replicate the result you report in the CoNLL04 dataset.

Question about reproducibility

Hello, I tried to reproduce the experiment reported in the paper, but the relation f1 of Bert-cased-base on the conll04 only reaches 63.4(report says 71.9). I didn't change any code. Do you know what's wrong with it? Did you use any other tricks?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.