Update README.md

268a441 verified about 1 month ago

No virus

8.37 kB

	---
	language:
	- pt
	thumbnail: Portuguese BERT for the Legal Domain
	tags:
	- sentence-transformers
	- transformers
	- bert
	- pytorch
	- sentence-similarity
	license: mit
	pipeline_tag: sentence-similarity
	datasets:
	- stjiris/portuguese-legal-sentences-v0
	- assin
	- assin2
	- stsb_multi_mt
	widget:
	- source_sentence: "O advogado apresentou as provas ao juíz."
	sentences:
	- "O juíz leu as provas."
	- "O juíz leu o recurso."
	- "O juíz atirou uma pedra."
	model-index:
	- name: BERTimbau
	results:
	- task:
	name: STS
	type: STS
	metrics:
	- name: Pearson Correlation - assin Dataset
	type: Pearson Correlation
	value: 0.7800806555562139
	- name: Pearson Correlation - assin2 Dataset
	type: Pearson Correlation
	value: 0.841456941132706
	- name: Pearson Correlation - stsb_multi_mt pt Dataset
	type: Pearson Correlation
	value: 0.8506042636740455
	---

	[![INESC-ID](https://www.inesc-id.pt/wp-content/uploads/2019/06/INESC-ID-logo_01.png)](https://www.inesc-id.pt/projects/PR07005/)

	[![A Semantic Search System for Supremo Tribunal de Justiça](https://rufimelo99.github.io/SemanticSearchSystemForSTJ/_static/logo.png)](https://rufimelo99.github.io/SemanticSearchSystemForSTJ/)

	Work developed as part of [Project IRIS](https://www.inesc-id.pt/projects/PR07005/).

	Thesis: [A Semantic Search System for Supremo Tribunal de Justiça](https://rufimelo99.github.io/SemanticSearchSystemForSTJ/)

	# stjiris/bert-large-portuguese-cased-legal-tsdae-mkd-nli-sts-v0 (Legal BERTimbau)
	This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
	stjiris/bert-large-portuguese-cased-legal-tsdae-mkd-nli-sts-v0 derives from stjiris/bert-large-portuguese-cased-legal-mlm (legal variant of [BERTimbau](https://huggingface.co/neuralmind/bert-large-portuguese-cased) large).

	It was trained using the TSDAE technique with a learning rate 1e-5 [Legal Sentences from +-30000 documents](https://huggingface.co/datasets/stjiris/portuguese-legal-sentences-v1.0) 21.2k training steps (best performance for our semantic search system implementation)

	This model was subjected to Multilingual Knowledge Distillation technique (mkd). For the Multilingual Knowledge Distillation process, the teacher model was 'sentence-transformers/stsb-roberta-large', the supposed supported language as English and the language to learn was portuguese
	The dataset used was: TED 2020 – Parallel Sentences Corpus. TED 2020 contains around 4000 TED and TED-X transcripts from July 2020. These transcripts were translated by volunteers into more than 100 languages, adding up to a total of 10 544 174 sentences.

	The model was presented to NLI data. 16 batch size, 2e-5 lr

	It was trained for Semantic Textual Similarity, being submitted to a fine tuning stage with the [assin](https://huggingface.co/datasets/assin), [assin2](https://huggingface.co/datasets/assin2), [stsb_multi_mt pt](https://huggingface.co/datasets/stsb_multi_mt) datasets. 'lr': 1e-5


	## 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 = ["Isto é um exemplo", "Isto é um outro exemplo"]

	model = SentenceTransformer('stjiris/bert-large-portuguese-cased-legal-tsdae-mkd-nli-sts-v0')
	embeddings = model.encode(sentences)
	print(embeddings)
	```
	## Usage (HuggingFace Transformers)
	```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 = ['This is an example sentence', 'Each sentence is converted']

	# Load model from HuggingFace Hub
	tokenizer = AutoTokenizer.from_pretrained('stjiris/bert-large-portuguese-cased-legal-tsdae-mkd-nli-sts-v0')
	model = AutoModel.from_pretrained('stjiris/bert-large-portuguese-cased-legal-tsdae-mkd-nli-sts-v0')

	# 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)
	```


	## Full Model Architecture
	```
	SentenceTransformer(
	(0): Transformer({'max_seq_length': 514, 'do_lower_case': False}) with Transformer model: BertModel
	(1): Pooling({'word_embedding_dimension': 1028, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
	)
	```
	## Citing & Authors

	### Contributions
	[@rufimelo99](https://github.com/rufimelo99)

	If you use this work, please cite:

	```bibtex
	@InProceedings{MeloSemantic,
	author="Melo, Rui
	and Santos, Pedro A.
	and Dias, Jo{\~a}o",
	editor="Moniz, Nuno
	and Vale, Zita
	and Cascalho, Jos{\'e}
	and Silva, Catarina
	and Sebasti{\~a}o, Raquel",
	title="A Semantic Search System for the Supremo Tribunal de Justi{\c{c}}a",
	booktitle="Progress in Artificial Intelligence",
	year="2023",
	publisher="Springer Nature Switzerland",
	address="Cham",
	pages="142--154",
	abstract="Many information retrieval systems use lexical approaches to retrieve information. Such approaches have multiple limitations, and these constraints are exacerbated when tied to specific domains, such as the legal one. Large language models, such as BERT, deeply understand a language and may overcome the limitations of older methodologies, such as BM25. This work investigated and developed a prototype of a Semantic Search System to assist the Supremo Tribunal de Justi{\c{c}}a (Portuguese Supreme Court of Justice) in its decision-making process. We built a Semantic Search System that uses specially trained BERT models (Legal-BERTimbau variants) and a Hybrid Search System that incorporates both lexical and semantic techniques by combining the capabilities of BM25 and the potential of Legal-BERTimbau. In this context, we obtained a {\$}{\$}335{\backslash}{\%}{\$}{\$}335{\%}increase on the discovery metric when compared to BM25 for the first query result. This work also provides information on the most relevant techniques for training a Large Language Model adapted to Portuguese jurisprudence and introduces a new technique of Metadata Knowledge Distillation.",
	isbn="978-3-031-49011-8"
	}


	@inproceedings{souza2020bertimbau,
	author = {F{\'a}bio Souza and
	Rodrigo Nogueira and
	Roberto Lotufo},
	title = {{BERT}imbau: pretrained {BERT} models for {B}razilian {P}ortuguese},
	booktitle = {9th Brazilian Conference on Intelligent Systems, {BRACIS}, Rio Grande do Sul, Brazil, October 20-23 (to appear)},
	year = {2020}
	}

	@inproceedings{fonseca2016assin,
	title={ASSIN: Avaliacao de similaridade semantica e inferencia textual},
	author={Fonseca, E and Santos, L and Criscuolo, Marcelo and Aluisio, S},
	booktitle={Computational Processing of the Portuguese Language-12th International Conference, Tomar, Portugal},
	pages={13--15},
	year={2016}
	}

	@inproceedings{real2020assin,
	title={The assin 2 shared task: a quick overview},
	author={Real, Livy and Fonseca, Erick and Oliveira, Hugo Goncalo},
	booktitle={International Conference on Computational Processing of the Portuguese Language},
	pages={406--412},
	year={2020},
	organization={Springer}
	}
	@InProceedings{huggingface:dataset:stsb_multi_mt,
	title = {Machine translated multilingual STS benchmark dataset.},
	author={Philip May},
	year={2021},
	url={https://github.com/PhilipMay/stsb-multi-mt}
	}

	```