Skip to content

Gk074/NLP-Unstructured-Data-Summarizer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Faithful Meeting Minutes Generator (MoM)

Research-driven NLP pipeline for structured, evidence-grounded meeting minutes generation from long multi-speaker transcripts.

Key Features

  • Embedding-based topic segmentation
  • Decision and action item extraction
  • Evidence span attribution
  • Structured JSON-constrained output (Pydantic)
  • Markdown MoM rendering
  • Designed to mitigate hallucination and long-context bias

Architecture

Transcript → Parsing → Topic Segmentation → Salience Scoring → Decision/Action Extraction → Structured MoM JSON → Markdown Output

Setup

1. Create Python 3.11 environment

py -3.11 -m venv .venv
.\.venv\Scripts\activate
pip install -r requirements.txt

About

NLP pipeline for converting long meeting transcripts into faithful minutes, decisions, action items, and structured summaries.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages