|
|
--- |
|
|
library_name: keras |
|
|
tags: |
|
|
- sentence-similarity |
|
|
--- |
|
|
|
|
|
## Model description |
|
|
|
|
|
This repo contains the model and the notebook for fine-tuning BERT model on SNLI Corpus for Semantic Similarity. [Semantic Similarity with BERT](https://keras.io/examples/nlp/semantic_similarity_with_bert/). |
|
|
|
|
|
Full credits go to [Mohamad Merchant](https://twitter.com/mohmadmerchant1) |
|
|
|
|
|
Reproduced by [Vu Minh Chien](https://www.linkedin.com/in/vumichien/) |
|
|
|
|
|
Motivation: Semantic Similarity determines how similar two sentences are, in terms of what they mean. The fine-tuned BERT model takes two sentences as inputs and outputs a similarity score for these two sentences. |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
This example demonstrates the use of SNLI (Stanford Natural Language Inference) Corpus to predict semantic sentence similarity with Transformers. |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
|
|
|
| Hyperparameters | Value | |
|
|
| :-- | :-- | |
|
|
| name | Adam | |
|
|
| learning_rate | 9.999999747378752e-06 | |
|
|
| decay | 0.0 | |
|
|
| beta_1 | 0.8999999761581421 | |
|
|
| beta_2 | 0.9990000128746033 | |
|
|
| epsilon | 1e-07 | |
|
|
| amsgrad | False | |
|
|
| training_precision | float32 | |
|
|
|
|
|
|
|
|
## Model Plot |
|
|
|
|
|
<details> |
|
|
<summary>View Model Plot</summary> |
|
|
|
|
|
 |
|
|
|
|
|
</details> |
