Skip to content
#

rouge-metric

Here are 47 public repositories matching this topic...

In modern international business, conversations often shift between languages. Transcript AI bridges this gap by utilizing Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) to ensure no context is lost in translation. It doesn't just transcribe; it understands business intent.

  • Updated Jun 27, 2026
  • Python

This repository explores the use of advanced sequence-to-sequence networks and transformer models, such as BERT, BART, PEGASUS, and T5, for summarizing multi-text documents in the medical domain. It leverages extensive datasets like CORD-19 and a Biomedical Abstracts dataset from Hugging Face to fine-tune these models.

  • Updated May 17, 2024
  • Jupyter Notebook

Unsupervised approach for inducing dialogue schemas from domain-specific conversations. This repository houses the source code and research findings from the application of cutting-edge NLP and ML techniques to dialogue systems.

  • Updated May 27, 2023
  • Python

Implementation of an interactive chatbot for summarizing legal and policy documents. Includes data preprocessing (cleaning, tokenization, hierarchical chunking), extractive TF-IDF baselines, and fine-tuned abstractive models (DistilBART, LED). Integrates a retrieval layer for document relevance and uses ROUGE, BLEU, and cosine similarity metrics.

  • Updated Jan 16, 2026
  • Jupyter Notebook

Improve this page

Add a description, image, and links to the rouge-metric topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the rouge-metric topic, visit your repo's landing page and select "manage topics."

Learn more