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.
Parameters:
| 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.
References:
[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