L

Legal BERTimbau Sts Large Ma V3

Developed by rufimelo
Portuguese legal domain sentence similarity model based on BERTimbau large model, supporting 1024-dimensional vector representation
Downloads 407
Release Time : 9/21/2022

Model Overview

This is a sentence transformation model optimized for the Portuguese legal domain, capable of mapping sentences and paragraphs into a 1024-dimensional vector space, suitable for tasks such as semantic search and clustering.

Model Features

Legal domain optimization
Specifically optimized for Portuguese legal texts, excelling in legal domain tasks
High-quality vector representation
Generates 1024-dimensional high-quality sentence embeddings, suitable for various downstream tasks
Multi-dataset training
Fine-tuned on multiple Portuguese datasets including assin, assin2, and stsb_multi_mt

Model Capabilities

Sentence similarity calculation
Semantic search
Text clustering
Legal text analysis

Use Cases

Legal text processing
Legal document similarity analysis
Compare semantic similarity between different legal documents or clauses
Achieved a Pearson correlation coefficient of 0.847 on the assin2 dataset
Legal Q&A system
Build a legal Q&A system based on semantic matching
Information retrieval
Legal case retrieval
Retrieve relevant legal cases based on query statements
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase