Comments (2)
Particularly, in the paper, DMBERT without Boot also performed pretty good. So I want to reproduce DMBERT with out extra data also.
from adv-ed.
Hi, thanks for your interest in our work.
- The method introduced in Section 3.4 is for semi-supervised and distant supervision settings. If there is no extra unlabeled data, the process cannot be performed. And the process in Section 3.4 is not used for dev and test sets.
- I cannot recall the exact number. The trigger-based latent instance discovery process is performed on the whole NYT corpus and this filters most of the sentences out.
- If you only want to run DMBERT in the supervised setting, I will refer to the codes for our recent work (https://github.com/THU-KEG/MAVEN-dataset/tree/main/baselines/DMBERT), which implements DMBERT in a relatively modern and cleaner way.
from adv-ed.
Related Issues (13)
- 您好 HOT 1
- Dscore_G参数写错了吧 HOT 1
- NA标签计算问题 HOT 5
- 关于数据划分 HOT 2
- 是否抽取事件论元
- 关于论文中Generator的一些问题请教 HOT 1
- 对作者的评测代码有一点疑问
- dataprocess HOT 1
- DMCNN HOT 1
- 关于数据event的有无的问题 HOT 1
- 关于远程监督方面的问题 HOT 1
- 如何划分`TrainA_conf`和`TrainA_unconf` HOT 1
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 adv-ed.