Git Product home page Git Product logo

kgan's Introduction

Hi 😀, I'm Qihuang Zhong

ABOUT ME

  • 👨‍🎓 I'm Qihuang Zhong, a phD student at Wuhan University, China.
  • 🧑‍💻 My research interests lie in the deep learning for NLP, such as discriminative language model pretraining, model adaptation, aspect-based sentiment analysis and etc.
  • 🤔 More recently, I mainly focus on chain-of-thought and large language model.
  • 👉 [Google Scholar] [Page]

Metrics

kgan's People

Contributors

whu-zqh 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  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

kgan's Issues

entity_embeddings的问题

您好,我现在在使用您的程序训练,我目前成功训练了Restaurant和Laptop,Twitter的数据集我在论文原作者那找到了。但是代码中的entity_embeddings_distmult_200.txt和entity_embeddings_analogy_400.txt我现在不知道可以在哪找到,搜索了一下也没有看到,请问您能否分享一下这两个文件的下载链接或者告知我获取方式吗?非常感谢您的解答。

数据集

你好,感谢开源代码,我想问下数据集中的/0,/n,/p表示是什么意思?

main_total有问题

from model.bert_vanill import BERT_vanilla这个模块作者可以上传不,谢谢

图文件问题

请问semeval_laptop_graph_analogy.pkl这种文件是怎么生成的?有相应的代码么?

dataset_npy问题

你好,请问怎么使用四个git-lfs文件或者怎么将git-lfs文件转化成npy和npz文件,非常感谢解答

utils报错

Traceback (most recent call last):
File "D:\研究生文件\文献\自然语言处理\代码集\KGAN-2.0\KGAN-2.0\main_total.py", line 493, in
a_acc, a_f1, a_time = train_bert(args, times=i)
File "D:\研究生文件\文献\自然语言处理\代码集\KGAN-2.0\KGAN-2.0\main_total.py", line 193, in train_bert
dataset, graph_embeddings, n_train, n_test = build_dataset(args=args, is_bert=True)
File "D:\研究生文件\文献\自然语言处理\代码集\KGAN-2.0\KGAN-2.0\utils.py", line 718, in build_dataset
dataset, vocab = load_data_dep_bert(ds_name=args.ds_name, is_bert = args.is_bert)
File "D:\研究生文件\文献\自然语言处理\代码集\KGAN-2.0\KGAN-2.0\utils.py", line 535, in load_data_dep_bert
train_set = pad_seq(dataset=train_set, field='adj', max_len=max_bert_len, symbol=-1)
File "D:\研究生文件\文献\自然语言处理\代码集\KGAN-2.0\KGAN-2.0\utils.py", line 31, in pad_seq
((0, max_len-dataset[i][field].shape[0]), (0, max_len-dataset[i][field].shape[0])), 'constant')
AttributeError: 'tuple' object has no attribute 'shape'
跑main-total的时候出现了这个错误,显示dataset[i][field]是元组,没办法和整数做减法,然后这里改了之后上一行np.pad(dataset[i][field]也有问题,因为它是元组,填充的时候显示ValueError: could not broadcast input array from shape (11,11) into shape (11,),不知道为什么别人跑好像没有问题,是不是版本不对呀,我用的是python3.9

论文

你好!请问你们论文投的是哪个期刊?

bert实现的参数问题

在进行模型的Bert实现的训练过程中,我使用的参数和学习率与默认参数一致,但是训练结果很差,模型对训练集的拟合程度甚至无法达到50%,请问是参数的问题吗,如果是,请问Bert模型的训练参数是怎样设置的呢?

Wordnet

您好!感谢您的代码,请问wordnet在代码中是如何被使用的呢?

数据集

您好,下载了您的代码,但是没有看见twitter数据集,请问Twitter数据集在哪可以下载;另外entity_embeddings文件应该放在哪个位置呢。万分感谢!!!

模型的bert实现

您好,我目前在使用您的模型进行训练,但是关于模型的Bert实现我并没有在代码中找到,请问模型的Bert实现何时能够分享?

关于跑bert时遇到的问题

跑的时候遇到这个:RuntimeError: CUDA error: device-side assert triggered
报一大串这种:/pytorch/aten/src/ATen/native/cuda/Indexing.cu:658: indexSelectLargeIndex: block: [146,0,0], thread: [38,0,0] Assertion srcIndex < srcSelectDimSize failed.
然后最后指向 squeeze_embedding 中的 x = x[x_sort_idx]

网上搜是说输入长度比Bert规定要大,请问应该怎么解决?

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.