Comments (1)
I got the reason. The reason is small dataset with very few batches. If you replace the dataset with the original tacred, you will not get this performance. The original dataset is not open sourced. So you have to buy it first.
from gcn-over-pruned-trees.
Related Issues (20)
- Influence on finetuning word embeddings
- Speedup training 10 times by one line of code HOT 1
- Implement of self loop HOT 1
- A little confuse on the code in func. head_to_tree in tree.py HOT 2
- Question on SemEval2010_task8 dataset HOT 4
- Why is your model stable every time it runs, while mine is unstable? I have set the seed. HOT 1
- Using fine-tune word embedding in the evaluation phase HOT 1
- A bug: subj_mask and obj_mask don't mask the padding tokens
- The number of GCN layers is the best for experiment?
- About dataset of SemEval 2010 task8 HOT 1
- Can the model be adjusted for sentence classification instead of sequence labeling with a [CLS] token?
- 你好,我想问一下数据集中的head是什么意思呢?
- Hi, I just want to ask, what does head mean in the dataset? HOT 3
- Memory issue
- Higher Loss Value HOT 6
- eval.py error HOT 6
- Meaning of "stanford_head" in given dataset HOT 1
- SemEval 2010 Task 8 Dataset is not used
- all predicted values are “no_relation”, and the Precision value is 100%, the Recall value is 0, and the value of dev_f1 is also 0. HOT 3
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 gcn-over-pruned-trees.