Blackstone
Legal Text Processor
Develops an NLP pipeline and model for processing long-form legal text
A spaCy pipeline and model for NLP on unstructured legal text.
641 stars
39 watching
101 forks
Language: Python
last commit: 8 months ago
Linked from 1 awesome list
caselawlawlegaltechnlpspacy-models
Related projects:
Repository | Description | Stars |
---|---|---|
| A tool for processing Coq and Lean 4 code embedded in text documents | 237 |
| Automated table detection and extraction using deep learning | 198 |
| Evaluates the legal knowledge of large language models using a custom benchmarking framework. | 273 |
| Decouples software implementation from underlying logic using LLMs to automate parsing of structured data | 392 |
| Wraps the Stanza NLP library to use Stanford models with spaCy | 726 |
| Develops and trains a large-scale, parameterized model for legal question answering and text generation | 105 |
| This repository contains source files and training scripts for language models. | 12 |
| A DSL for building custom NLP patterns from manual language rules | 65 |
| A Python wrapper for a Java-based natural language processing toolset. | 923 |
| Trains a language model using a RoBERTa architecture on high-quality Polish text data | 33 |
| Pre-trained language models for biomedical natural language processing tasks | 560 |
| Develops an end-to-end model for multiple visual perception and reasoning tasks using a single encoder, decoder, and large language model. | 1,336 |
| A Ruby wrapper around Apache OpenNLP's natural language processing tools | 11 |
| A collection of libraries and tools for Natural Language Processing | 473 |