Comments (5)
Hi, there. Thanks for the comments.
Since there are no negative samples in the training set, the model cannot well predict N/A event.
Besides, documents without event instances would be removed during pre-processing (for DuEE-fin only).
You can absolutely add an additional N/A event and negative samples with some code adaptation to provide a more accurate N/A instance prediction.
from docee.
Thanks for replying. I find another problem about what if there are more than one arguments in an argument role. Does the model take that into account?
from docee.
Thanks for replying. I find another problem about what if there are more than one arguments in an argument role. Does the model take that into account?
Yes, PTPCG can predict more than one argument for each role. This is a common practice when we participated in LIC'21 (DuEE-fin):
- your data can be formatted as something like below:
"recguid_eventname_eventdict_list": [
[
0,
"EquityPledge",
{
"Pledger": ["李云春"],
"PledgedShares": ["40789194股", "123123股"],
"Pledgee": ["招商证券股份有限公司"],
"TotalHoldingShares": ["162103218股"],
"TotalHoldingRatio": ["11.55%"],
"TotalPledgedShares": ["86304393股"],
"StartDate": ["2015年5月7日"],
"EndDate": ["2016年5月6日"],
"ReleasedDate": ["2016年5月6日"]
}
]
]
- make code adaptations to fit such a format (e.g. 1) write new features in data helper to keep multi-arg roles ; 2) multi-hot encoding rather than one-hot when calculating role's classification loss)
- important: set
unique_role=False
when predicting argument roles:predict_span_role(batch_span_emb, unique_role=False)
However, since the other baselines (Doc2EDAG, GIT) are designed on ChFinAnn, they cannot predict many arguments for one role in a single event instance. To make fair comparisons with these systems, we set PTPCG to only predict one argument each time (unique_role=True
), and publish the results in our paper.
from docee.
Thanks for replying. I am trying to modify the code.
from docee.
Thanks for replying. I am trying to modify the code.
不知道是否有改好可以跑的代码
from docee.
Related Issues (20)
- doc_lang=self.setting.doc_lang报错 HOT 3
- 这个库里面哪些代码是ptpcg这个算法用到的 HOT 29
- 新数据集的训练 HOT 18
- PTPCG 分布式训练的效率 HOT 8
- 关于trigger HOT 3
- 触发词的问题 HOT 10
- 训练 teacher prob 的问题 HOT 7
- wikievents 等英文数据集实验 HOT 23
- ner 这块的问题 HOT 7
- ner 参数设置的问题 HOT 1
- 在计算相似度时是否忽略了实体的相对位置 HOT 1
- Failed to reproduce the result with inference.py HOT 2
- Transformer相关的问题 HOT 2
- loss weight mismatch
- some doubts HOT 1
- 代码疑似错误 HOT 4
- 请问可以提供各个模型的checkpioint吗? HOT 4
- 怎么加bert模型呢 HOT 3
- Number of gold arguments for ChFinAnn HOT 11
- 请问怎么查看到中文格式的事件预测结果? HOT 6
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from docee.