destwang / dcn Goto Github PK
View Code? Open in Web Editor NEWDynamic Connected Networks for Chinese Spelling Check
License: Apache License 2.0
Dynamic Connected Networks for Chinese Spelling Check
License: Apache License 2.0
请问作者,我从训练数据集中发现【unk】,请问添加unk的目的是什么?
Hi,can you release your code recently?
I don't know how do you generate data. After I train my model, I can't get predictions.
您好,在运行sh train.sh了训练模型完成之后,如何在SIGHAN上测试模型得到您展示的结果呢?
The dataset link need username and code, but i only see the code.
Can you provide the username to download the train set?
Thank you.
大神你好,我看之前的issue说要开放预训练代码,请问有这个计划吗?
谢谢
In the file transformers/modeling_dcn.py, line 550.
self.word_pinyin_idx = torch.tensor(self.word_pinyin_idx, device="cuda")
I think device="cuda"
would cause lots of bugs. Maybe you can fix it, or maybe I'm wrong. Thanks.
您好,我这边本地测试,用的2080TI,12G显存,batch size只能设置为6才不会OOM,这正常吗?您这边用的什么机器可以跑bz=32?
您好,感谢您公开了代码,我按照您的流程跑了一下,只是batch_size设置不同,到那时结果大概低一个百分点;另外分析sighan15的测试集结果,发现Truth数据集中有一些错误,比如: (pid=A2-1311-2) 这女人告所他的大学在那里。 这里预测出来告诉,但是truth中实际上是没有这个错误的,所以数据集是没有经过清洗是吗?
Traceback (most recent call last):
File "train_DCN.py", line 511, in
main()
File "train_DCN.py", line 228, in main
model = DCNForMaskedLM.from_pretrained(
File "/home/zhaojianhui/DCN-main/transformers/modeling_utils.py", line 671, in from_pretrained
model = cls(config, *model_args, **model_kwargs)
File "/home/zhaojianhui/DCN-main/transformers/modeling_dcn.py", line 1124, in init
self.cls = BertOnlyMLMHead(config)
File "/home/zhaojianhui/DCN-main/transformers/modeling_dcn.py", line 586, in init
self.predictions = BertLMPredictionHead(config)
File "/home/zhaojianhui/DCN-main/transformers/modeling_dcn.py", line 543, in init
self.pinyin_embeddings = nn.Embedding(config.pinyin_vocab_size,
AttributeError: 'BertConfig' object has no attribute 'pinyin_vocab_size'
论文中的最好表现是需要在wiki data上预训练,这部分预训练具体是咋做的,数据是哪些,可以答疑解惑一下么。。
********* Evaluation Test sighan15 Sentence-level ************
1100 1100
detect_sent_precision=0.756432, detect_sent_recall=0.801818, detect_Fscore=0.778464
correct_sent_precision=0.728988, correct_sent_recall=0.772727, correct_Fscore=0.750221
结果接近没有预训练的Roberta-DCN,batch_size 为30.
如题,是直接在train.txt上训练,然后在sighan15 数据集上验证结果么,为啥子不用切分train.txt之类的操作
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.