Data

Tools

Indexes

Applications

Experiments

Open Source Science

docutron

Docutron Toolkit: detection and segmentation analysis for legal data extraction over documents.

https://github.com/louisbrulenaudet/docutron

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (13.5%) to scientific vocabulary

Keywords

cv2 detecron2 detection document legal legaltech legaltools llm machine-learning nlp ocr ocr-recognition preprocessing
Last synced: 6 months ago · JSON representation

Repository

Docutron Toolkit: detection and segmentation analysis for legal data extraction over documents.

Basic Info
Statistics
  • Stars: 25
  • Watchers: 2
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Topics
cv2 detecron2 detection document legal legaltech legaltools llm machine-learning nlp ocr ocr-recognition preprocessing
Created over 2 years ago · Last pushed over 2 years ago
Metadata Files
Readme Funding License Code of conduct Citation Security

README.md

Docutron Toolkit: detection and segmentation analysis for legal data extraction over documents

Python License Maintainer

Docutron is a tool designed to facilitate the extraction of relevant information from legal documents, enabling professionals to create datasets for fine-tuning language models (LLM) for specific legal domains.

Legal professionals often deal with vast amounts of text data in various formats, including legal documents, contracts, regulations, and case law. Extracting structured information from these documents is a time-consuming and error-prone task. Docutron simplifies this process by using state-of-the-art computer vision and natural language processing techniques to automate the extraction of key information from legal documents.

Docutron testing image

Whether you are delving into contract analysis, legal document summarization, or any other legal task that demands meticulous data extraction, Docutron stands ready to be your reliable technical companion, simplifying complex legal workflows and opening doors to new possibilities in legal research and analysis.

Tech Stack

Language: Python +3.9.0

Dependencies

The script relies on the following Python libraries: - PyTorch - Detectron2 - Cv2

Installation

Clone the repo

sh git clone https://github.com/louisbrulenaudet/docutron.git

Roadmap

  • [x] Complete the first training and testing
  • [x] Create the first dataset for labeling process
  • [ ] Create a second version of the dataset in order to handle more cases
  • [ ] Implementing in a structured architecture

Citing this project

If you use this code in your research, please use the following BibTeX entry. ```BibTeX

@misc{louisbrulenaudet2023, author = {Louis Brul Naudet}, title = {Docutron Toolkit: detection and segmentation analysis for legal data extraction over documents}, howpublished = {\url{https://github.com/louisbrulenaudet/docutron}}, year = {2023} } ```

Feedback

If you have any feedback, please reach out at louisbrulenaudet@icloud.com.

Owner

  • Name: Louis Brulé Naudet
  • Login: louisbrulenaudet
  • Kind: user
  • Location: Paris
  • Company: Université Paris-Dauphine (Paris Sciences et Lettres - PSL)

Research in business taxation and development (NLP, LLM, Computer vision...), University Dauphine-PSL 📖 | Backed by the Microsoft for Startups Hub program

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Committers

Last synced: about 2 years ago

All Time
  • Total Commits: 9
  • Total Committers: 1
  • Avg Commits per committer: 9.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 9
  • Committers: 1
  • Avg Commits per committer: 9.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Louis Brulé Naudet l****t@i****m 9

Issues and Pull Requests

Last synced: about 1 year ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels