mrp
/

SCT_BERT_Base

Sentence Similarity

sentence-transformers

feature-extraction

Inference Endpoints

Model card Files Files and versions Community

SCT_BERT_Base / README.md

mrp's picture

mrp

Update README.md

e8d2ec5 7 months ago

|

raw history blame contribute delete

No virus

3.15 kB

	---
	pipeline_tag: sentence-similarity
	license: apache-2.0
	tags:
	- sentence-transformers
	- feature-extraction
	- sentence-similarity
	- transformers
	language:
	- en
	datasets:
	- snli
	- multi_nli
	metrics:
	- spearmanr
	model-index:
	- name: mrp/SCT_BERT_Base
	results:
	- task:
	type: STS # Required. Example: automatic-speech-recognition
	name: STS # Optional. Example: Speech Recognition
	dataset:
	type: Similarity # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
	name: STS12 # Required. A pretty name for the dataset. Example: Common Voice (French)
	metrics:
	- type: spearmanr # Required. Example: wer. Use metric id from https://hf.co/metrics
	value: 78.83 # Required. Example: 20.90
	name: Test spearmanr # Optional. Example: Test WER
	verified: False # Optional. If true, indicates that evaluation was generated by Hugging Face (vs. self-reported).

	- name: mrp/SCT_BERT_Base
	results:
	- task:
	type: STS # Required. Example: automatic-speech-recognition
	name: STS # Optional. Example: Speech Recognition
	dataset:
	type: Similarity # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
	name: STS13 # Required. A pretty name for the dataset. Example: Common Voice (French)
	metrics:
	- type: spearmanr # Required. Example: wer. Use metric id from https://hf.co/metrics
	value: 78.02 # Required. Example: 20.90
	name: Test spearmanr # Optional. Example: Test WER
	verified: False # Optional. If true, indicates that evaluation was generated by Hugging Face (vs. self-reported).
	---


	# mrp/SCT_BERT_Base

	This is a [SCT](https://github.com/mrpeerat/SCT) model: It maps sentences to a dense vector space and can be used for tasks like semantic search.



	## Usage

	Using this model becomes easy when you have [SCT](https://github.com/mrpeerat/SCT) installed:

	```
	pip install -U git+https://github.com/mrpeerat/SCT
	```

	Then you can use the model like this:

	```python
	from sentence_transformers import SentenceTransformer
	sentences = ["This is an example sentence", "Each sentence is converted"]

	model = SentenceTransformer('mrp/SCT_BERT_Base')
	embeddings = model.encode(sentences)
	print(embeddings)
	```



	## Evaluation Results



	For an automated evaluation of this model, see the Sentence Embeddings Benchmark: [Semantic Textual Similarity](https://github.com/mrpeerat/SCT#main-results---sts)


	## Citing & Authors

	```bibtex
	@article{limkonchotiwat-etal-2023-sct,
	title = "An Efficient Self-Supervised Cross-View Training For Sentence Embedding",
	author = "Limkonchotiwat, Peerat and
	Ponwitayarat, Wuttikorn and
	Lowphansirikul, Lalita and
	Udomcharoenchaikit, Can and
	Chuangsuwanich, Ekapol and
	Nutanong, Sarana",
	journal = "Transactions of the Association for Computational Linguistics",
	year = "2023",
	address = "Cambridge, MA",
	publisher = "MIT Press",
	}
	```