scibert-nli /
This is the model [SciBERT]( [1] fine-tuned on the [SNLI]( and the [MultiNLI]( datasets using the [`sentence-transformers` library]( to produce universal sentence embeddings [2].
The model uses the original `scivocab` wordpiece vocabulary and was trained using the **average pooling strategy** and a **softmax loss**.
**Base model**: `allenai/scibert-scivocab-cased` from HuggingFace's `AutoModel`.
**Training time**: ~4 hours on the NVIDIA Tesla P100 GPU provided in Kaggle Notebooks.
| Parameter | Value |
| Batch size | 64 |
| Training steps | 20000 |
| Warmup steps | 1450 |
| Lowercasing | True |
| Max. Seq. Length | 128 |
**Performances**: The performance was evaluated on the test portion of the [STS dataset]( using Spearman rank correlation and compared to the performances of a general BERT base model obtained with the same procedure to verify their similarity.
| Model | Score |
| `scibert-nli` (this) | 74.50 |
| `bert-base-nli-mean-tokens`[3]| 77.12 |
An example usage for similarity-based scientific paper retrieval is provided in the [Covid Papers Browser]( repository.
[1] I. Beltagy et al, [SciBERT: A Pretrained Language Model for Scientific Text](
[2] A. Conneau et al., [Supervised Learning of Universal Sentence Representations from Natural Language Inference Data](
[3] N. Reimers et I. Gurevych, [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](