Comments (1)
Hi Shihan,
For some datasets, like NELL, we don't train on all the tuples in the graph so the train set is much smaller than the graph. Also, graph.txt contains the inverse relations that we don't train the RL agent.
Full_graph if there is just the sum of train/dev. It's only used to mask out the other positive answers during inference.
Hope that clarifies your questions!
-Shehzaad
from minerva.
Related Issues (20)
- Table 4 experiments HOT 7
- Reproduce Kinship, FB15k-237 results HOT 5
- sharing the pre-trained embeddings learned by Dismult HOT 1
- Reproduce WN18RR results HOT 7
- parameter settings used in paper
- train/dev/test split HOT 4
- Unable to load the saved_model HOT 4
- Encode the relation and entity ? HOT 4
- Question in code/model/trainer.py HOT 1
- num_rollouts HOT 2
- Testing problem HOT 7
- How do you extract the general rules from the trained policy(like the (i) example in table 8)?
- the accuracy can be better after fine tune the function `calc_cum_discounted_reward ` as follows HOT 2
- Pytorch implementation for MINERVA HOT 1
- Export the mode using `tf.saved_model` and deploy it to production environment HOT 1
- On comparison of MINERVA with other KBE baselines
- meaning of last-step in return_next_actions
- Is this code an official implementation to the method in paper "Neuro-Symbolic Inductive Logic Programming with Logical Neural Networks"?
- How to process partially structured question?
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 minerva.