Evaluation code for various unsupervised automated metrics for Natural Language Generation.

ROUGE automatic summarization evaluation toolkit. Support for ROUGE-[N, L, S, SU], stemming and stopwords in different languages, unicode text evaluation, CSV output.

Python ROUGE Score Implementation for Chinese Language Task (official rouge score)

Python implementation of ROUGE

Evaluation tools for image captioning. Including BLEU, ROUGE-L, CIDEr, METEOR, SPICE scores.

ROUGE L metric implementation using tensorflow ops

A serverless set of functions for evaluating whether incoming messages to an LLM system seem to contain instances of prompt injection; uses cascading cosine similarity and ROUGLE-L calculation against known good and bad prompts

This is a Pytorch implementation of a summarization model that is fine-tuned on the top of Google-T5 pre-trained model.

A news headline generator finetuned on T5-base.

Evaluation and agreement scripts for the DISCOSUMO project. Each evaluation script takes both manual annotations as automatic summarization output. The formatting of these files is highly project-specific. However, the evaluation functions for precision, recall, ROUGE, Jaccard, Cohen's kappa and Fleiss' kappa may be applicable to other domains too.

Text Summarizer is an NLP-driven application designed to provide concise summaries of large text documents. Leveraging advanced algorithms and machine learning techniques, this project streamlines the process of information retrieval, making it easier for users to grasp key points quickly.

Text summarization of Hotel reviews using Huggingface Transformers T5 and Bart

The TerminusAI is a lightweight, fine-tuned AI assistant designed to help users interact with the command line more effectively. Trained on real-world Q&A from Stack Overflow , this project leverages open-source LLMs TinyLlama fine-tuned with LoRA/QLoRA to provide contextual, accurate, and safe terminal guidance.