thunlp / chinese_nre Goto Github PK
View Code? Open in Web Editor NEWSource code for ACL 2019 paper "Chinese Relation Extraction with Multi-Grained Information and External Linguistic Knowledge"
License: MIT License
Source code for ACL 2019 paper "Chinese Relation Extraction with Multi-Grained Information and External Linguistic Knowledge"
License: MIT License
Is there any pre-trained model checkpoint I can use to test? Training takes too much time because of the batch_size
您好,论文中所有模型的F1值都是exclude other吗?
在test文档中,第一列的实体和第二列的实体顺序是否不可改变,必须是句子中先出现的在前,后出现的在后
Changing
self.weight_hh.data.set_(weight_hh_data)
to
with torch.no_grad():
self.weight_hh.data.set_(weight_hh_data)
did not help.
ValueError: At least 2 points are needed to compute area under curve, but x.shape = 0
auc曲线那里获取不到数据?
给的数据文件sense.txt最后一行"铛铛车"的embedding缺失了一小段数值,长度才175,其他都是201
在github上看见了你们组的论文,想了解一下sense.txt和sense_map.txt怎么生成呀?想学习一下你们的代码。请问sense.txt是在这里下载那个sense-vec.txt吗?https://cloud.tsinghua.edu.cn/d/76ab4a71efa541bd8eb3/
Thanks
模型里牵扯到的太多了所以不知道应该修改哪里的batch_size,看到显存占用只有980M,麻烦您能不能解答一下,非常感谢!
Traceback (most recent call last):
File "D:/pycharm/work/Chinese_NRE-master/main.py", line 187, in
train(data, configure.savemodel)
File "D:/pycharm/work/Chinese_NRE-master/main.py", line 97, in train
model = MGLattice_model(data)
File "D:\pycharm\work\Chinese_NRE-master\nn\framework.py", line 15, in init
self.encoder = BiLstmEncoder(data)
File "D:\pycharm\work\Chinese_NRE-master\nn\encoder.py", line 98, in init
self.forward_lstm = LatticeLSTM(lstm_input, lstm_hidden, data.gaz_dropout, data.gaz_alphabet.size(), data.gaz_emb_dim, data.pretrain_gaz_embedding, True, data.HP_fix_gaz_emb, self.gpu)
File "D:\pycharm\work\Chinese_NRE-master\nn\mglattice.py", line 262, in init
self.rnn = MultiInputLSTMCell(input_dim, hidden_dim)
File "D:\pycharm\work\Chinese_NRE-master\nn\mglattice.py", line 163, in init
self.reset_parameters()
File "D:\pycharm\work\Chinese_NRE-master\nn\mglattice.py", line 174, in reset_parameters
self.weight_hh.data.set_(weight_hh_data)
RuntimeError: set_storage is not allowed on Tensor created from .data or .detach()
想问一下对于论文中的公式1,为什么在代码中还要加上最大句长再加1?
return x + maxlen + 1
I re-labeled the FinRE dataset as FinRE-v2
with these rules below:
订单
to 订单
, 被下订单
relations so that can capture the characters between "provider" and "client"砍单
, 被砍单
: if 增持
and 减持
exist, there should have 订单
and 砍单
交易
, 签约
, 重组
]: more specific capture what kind of trading, eg. 买资
, 收购
, 持股
, 增持
or 减持
, etc.The entire relation classes schema:
unknown 0
注资 1
拥有 2
纠纷 3
自己 4
增持 5
重组 6
买资 7
签约 8
持股 9
交易 10
入股 11
转让 12
成立 13
分析 14
合作 15
帮助 16
发行 17
商讨 18
合并 19
竞争 20
订单 21
砍单 22
减持 23
合资 24
收购 25
借壳 26
欠款 27
被发行 28
被转让 29
被成立 30
被注资 31
被持股 32
被拥有 33
被收购 34
被帮助 35
被借壳 36
被买资 37
被欠款 38
被增持 39
拟收购 40
被减持 41
被分析 42
被入股 43
被拟收购 44
被重组 45
被下订单 46
被砍单 47
The re-labeled dataset is provided through Google Drive link on my Github repo: https://github.com/A-baoYang/NLP-techniques-chinese/tree/main/NLU/Classification/RelationClassification
您好,请问如果是一个新的数据集怎么进行预训练
请问文章什么时候可以放上来,想学习一下
您好,我阅读了您的代码,发现AttClassifier貌似是用于远程监督的包级别分类器,但是论文中却没有提及这一点,请问模型使用的这些数据集都是远程监督的数据集吗
训练集的前四句中,“东方航空”和“上航”既是unknown,也是“合并”关系,请问这种情况应该怎么处理呢?非常感谢您的回复~
“东方航空 上航 unknown 东方航空AH股临时停牌传将与上航合并
上航 东方航空 unknown 东方航空AH股临时停牌传将与上航合并
东方航空 上航 合并 东方航空AH股临时停牌传将与上航合并
上航 东方航空 合并 东方航空AH股临时停牌传将与上航合并”
为什么我算了算在colab免费gpu条件下得100个小时,就是这么久还是我操作有误?
Hello! I found the default batch size is set to be 1. Can we change it to a larger value for accelerating the training?
Besides, the training takes too much time for me. I wonder if something goes wrong in my setting. May you share the time you spend in your training.
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.