Update README.md

9cb0324 almost 2 years ago

No virus

4.18 kB

	---
	pipeline_tag: sentence-similarity
	language: fr
	tags:
	- sentence-similarity
	- transformers
	- Education
	- fr
	- flaubert
	- sentence-transformers
	- feature-extraction
	- xnli
	- stsb_multi_mt
	datasets:
	- xnli
	- stsb_multi_mt
	---

	# inokufu/bertheo

	A [sentence-transformers](https://www.SBERT.net) model fine-tuned on course sentences. It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

	## Details

	This model is based on the French flaubert-base-uncased pre-trained model [1, 2].

	It was first fine-tuned on our learning object (LO) sentences dataset. This dataset consists of a sample of 500k sentences of course descriptions. We used standard parameter settings for fine-tuning as mentioned in the original BERT paper [3]. This allows the model to improve its performance on the target task (Masked Language Model) for domain-specific sentences.

	It was then fine-tuned on a natural language inference task (XNLI) [4]. This task consists in training the model to recognize relations between sentences (contradiction, neutral, implication).

	It was then fine-tuned on a text semantic similarity task (on STS-fr data) [5]. This task consists in training the model to estimate the similarity between two sentences.

	This fine-tuning process allows our model to have a semantic representation of words that is much better than the one proposed by the base model.

	## Usage (Sentence-Transformers)

	Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:

	```
	pip install -U sentence-transformers
	```

	Then you can use the model like this:

	```python
	from sentence_transformers import SentenceTransformer
	sentences = ["Apprendre le python", "Devenir expert en comptabilité"]

	model = SentenceTransformer('inokufu/flaubert-base-uncased-xnli-sts-finetuned-education')
	embeddings = model.encode(sentences)
	print(embeddings)
	```



	## Usage (HuggingFace Transformers)
	Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

	```python
	from transformers import AutoTokenizer, AutoModel
	import torch


	#Mean Pooling - Take attention mask into account for correct averaging
	def mean_pooling(model_output, attention_mask):
	token_embeddings = model_output[0] #First element of model_output contains all token embeddings
	input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
	return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


	# Sentences we want sentence embeddings for
	sentences = ["Apprendre le python", "Devenir expert en comptabilité"]

	# Load model from HuggingFace Hub
	tokenizer = AutoTokenizer.from_pretrained('inokufu/flaubert-base-uncased-xnli-sts-finetuned-education')
	model = AutoModel.from_pretrained('inokufu/flaubert-base-uncased-xnli-sts-finetuned-education')

	# Tokenize sentences
	encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

	# Compute token embeddings
	with torch.no_grad():
	model_output = model(**encoded_input)

	# Perform pooling. In this case, mean pooling.
	sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

	print("Sentence embeddings:")
	print(sentence_embeddings)
	```

	## Evaluation Results

	STS (fr) score: 83.05%


	## Model Architecture
	```
	SentenceTransformer(
	(0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: FlaubertModel
	(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
	)
	```

	## References

	[1] https://hal.archives-ouvertes.fr/hal-02784776v3/document <br>
	[2] https://huggingface.co/flaubert/flaubert_base_uncased <br>
	[3] https://arxiv.org/abs/1810.04805 <br>
	[4] https://arxiv.org/abs/1809.05053 <br>
	[5] https://huggingface.co/datasets/stsb_multi_mt <br>