Benchmarking various Deep Learning models such as BERT, ALBERT, BiLSTMs on the task of sentence entailment using two datasets - MultiNLI and SNLI.
Benchmarking various Deep Learning models such as BERT, ALBERT, BiLSTMs on the task of sentence entailment using two datasets - MultiNLI and SNLI.
These correspond to the model benchmarks on 100k training samples of the MultiNLI dataset.
| Model | Validation accuracy | Validation loss | Training accuracy | Training loss |
|---|---|---|---|---|
| BiLSTM | 0.6104 | 0.8718 | 0.6014 | 0.8754 |
| BERT | 0.7906 | 0.8490 | 0.9690 | 0.0916 |
| ALBERT | 0.7110 | 0.7003 | 0.7405 | 0.6356 |
I know this is simply a benchmarking repository. I am trying to extend the model to take in sentences and return the label based on the model. But currently the model only gives the results of the metrics and the code is really complicated as the inputs and predictions are very complex sets of tensors, and I am being unable to attain the required information from these. It would be really kind of you to at least guide me to make the best out of this repository. Thanks!
As of now, the model is simply trained and a set of training accuracy and validation accuracy is recorded after the epochs in the base LSTM model. Can you also try to integrate the test snli dataset so that a better understanding of the entailment scores can be recorded?
Hi,
Can u pls share the train / test /dev datasets?
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
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.
