SentenceTransformer based on neuralmind/bert-large-portuguese-cased
This is a sentence-transformers model finetuned from neuralmind/bert-large-portuguese-cased. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
1from sentence_transformers import SentenceTransformer
23# Download from the 🤗 Hub4model = SentenceTransformer("sentence_transformers_model_id")5# Run inference6sentences =[7"o autor possuía..., ",8"a parte autora é servidor pública...",9"a parte autora é..."10]11embeddings = model.encode(sentences)12print(embeddings.shape)13# [3, 1024]1415# Get the similarity scores for the embeddings16similarities = model.similarity(embeddings, embeddings)17print(similarities)18# tensor([[1.0000, 1.0000, 0.8019],19# [1.0000, 1.0000, 0.8019],20# [0.8019, 0.8019, 1.0000]])
Diretoria de Inteligência Artificial, Ciência de Dados e Estatística do Tribunal de Justiça do Estado de Goiás (TJGO).
Citation
BibTeX
LexIris-pt / LexBert-pt
bibtex
1@inproceedings{santos-etal-2026-lexiris,
2 title = "{L}ex{I}ris-pt and {L}ex{B}ert-pt: Specialized Sentence Embeddings for Legal Similarity in {B}razilian {P}ortuguese",
3 author = "Santos, Willgnner Ferreira and
4 Viana, Jo{\~a}o Gabriel Grandotto and
5 J{\'u}nior, Ant{\^o}nio Pires de Castro and
6 Trindade, Fernando Ribeiro and
7 Silva, N{\'a}dia F{\'e}lix Felipe da",
8 editor = "Souza, Marlo and
9 de-Dios-Flores, Iria and
10 Santos, Diana and
11 Freitas, Larissa and
12 Souza, Jackson Wilke da Cruz and
13 Ribeiro, Eug{\'e}nio",
14 booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 1",
15 month = apr,
16 year = "2026",
17 address = "Salvador, Brazil",
18 publisher = "Association for Computational Linguistics",
19 url = "https://aclanthology.org/2026.propor-1.53/",
20 pages = "540--550",
21 ISBN = "979-8-89176-387-6",
22 abstract = "This work presents and evaluates two specialized sentence embedding models for the Portuguese legal domain, LexIris-pt and LexBert-pt, obtained through supervised fine-tuning of BERT-based models using pairs of initial petitions. We propose a comparative evaluation protocol along three fronts: (i) zero-shot inference with pretrained embeddings, (ii) supervised fine-tuning on these pairs, and (iii) vector retrieval with incremental clustering over a corpus of 20,000 initial petitions. The results show that fine-tuning consistently increases correlations with reference scores and improves performance in vector retrieval; additionally, the vector retrieval stage indicates that the metric configured in the index (cosine similarity or inner product) can change the granularity of the partitioning under a fixed threshold, reinforcing the need for joint calibration among the encoder, metric and threshold. After auditing by specialists from the partner institution, LexIris-pt and LexBert-pt were operationally adopted to support the screening and organization of repetitive claims and predatory litigation."
23}
Sentence Transformers
bibtex
1@inproceedings{reimers-2019-sentence-bert,
2 title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
3 author = "Reimers, Nils and Gurevych, Iryna",
4 booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
5 month = "11",
6 year = "2019",
7 publisher = "Association for Computational Linguistics",
8 url = "https://arxiv.org/abs/1908.10084",
9}
BERTIMBAU
bibtex
1@inproceedings{souza2020bertimbau,
2 author = {F{\'a}bio Souza and
3 Rodrigo Nogueira and
4 Roberto Lotufo},
5 title = {{BERT}imbau: pretrained {BERT} models for {B}razilian {P}ortuguese},
6 booktitle = {9th Brazilian Conference on Intelligent Systems, {BRACIS}, Rio Grande do Sul, Brazil, October 20-23 (to appear)},
7 year = {2020}
8}
