Comments (7)
Sorry for the late reply.
I do not value paper reproduction (such as TreeGen) now for 2 reasons. The first reason is that using a large model with NLP technique may be a more effective and simpler approach than AST-based program generation (e.g., http://arxiv.org/abs/2105.09938v1). And the second reason is that I found out that the quality and characteristics of dataset are more critical than model differences for many usecases.
So, the status of these paper-reproduction issues is pending.
Thank you for your comments!
from mlprogram.
Hi! Maybe I can help. What are the suggested next steps to have this work @HiroakiMikami?
from mlprogram.
Hi @HiroakiMikami apologies for the spam. Let me know if there is something specific that you suggest to look into to help with having pytorch TreeGen working!
from mlprogram.
Hi @HiroakiMikami apologies for the spam! Let me know if you do want help.
from mlprogram.
And the second reason is that I found out that the quality and characteristics of dataset are more critical than model differences for many usecases.
Hi Hiroaki,
I appreciate your response. I was wondering if you could clarify what you meant by that. Do you mean that all models perform relatively similar across all data sets? I wasn't quite sure how to interpret your response.
I am also curious, what type of model would you prefer then? NLP based ones? Grammar syntax based ones? Or something else?
thanks for your time again!
from mlprogram.
Another question, our of curiosity, if you do not value reproduction of papers anymore what do you value? Related, does this make your mlprogram repo obsolete for you (besides the fact it makes it easy for you to run experiments)?
Thanks for your time! Its appreciated.
from mlprogram.
Do you mean that all models perform relatively similar across all data sets?
That's almost right. I think all models show a similar performance if the used computational resource (e.g., model parameters, FLOPs, and training epochs) is almost the same.
Also, I think that dataset quality (e.g. the number of annotation mistakes, the code quality) is important. The performance of program synthesis may be limited by the quality of the dataset, not DNN model structures.
what type of model would you prefer then? NLP based ones? Grammar syntax based ones
I think NLP based one is enough for program synthesis. Grammer syntax based models reduce the syntax errors of the outputs. However, the inference procedure is very complex and cannot utilize GPU efficiently. So using NLP based models and filtering out the code with invalid syntax (like CodeXGLUE baselines) may be more efficient than using grammer syntax models.
if you do not value reproduction of papers anymore what do you value? Related, does this make your mlprogram repo obsolete for you (besides the fact it makes it easy for you to run experiments)?
I made and maintained this repository in order to make my experiments easy, so the purpose of mlprogram is not changed. But I should use transformers module as a model zoo.
from mlprogram.
Related Issues (20)
- Re-create Environment
- Fix metrics.reduce function
- Remove input from metrics
- Encode each element separately (action_sequence)
- Remove Field class
- Fix CSG Interpreter
- Performance improvement
- Run CI by using Python 3.6
- RL Synthesizer
- Multi-process RL synthesizer HOT 1
- Create benchmark configs HOT 3
- (CPU) distributed launcher HOT 1
- Delete workspace
- Refactor CI
- Change configs to simple python program
- Swap test <=> valid
- DreamCoder - Learning a DSL with wake sleep algorithm
- How is the target vector (program rules sequence) in TreeGen created during training? HOT 1
- nl_attention not found in ASTReader
- How to convert ActionSequence/AST to CODE?
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 mlprogram.