A simple python implementation of the Maximal Marginal Relevance (MMR) baseline system for text summarization.
Scripts for an upcoming blog "Extractive vs. Abstractive Summarization" for RaRe Technologies.
Agentic RAG with Llama-3.1-8b model Fine-tuned on medical conversational dataset
A set of serverless functions designed to assist in the monitoring of inputs to language models, including routine and specific inspection of the message queue, as well as event-driven triggering of more complex metric calculation based on (what will eventually be) configurable environment variables; alongside a suite of other tools/functions
Recalculating ROUGE scores for See et al. (2017) test outputs.
A systematic empirical comparison of five seq2seq encoder architectures (GRU, LSTM, Bi-LSTM, GRU+Attention, Transformer) for English→French neural machine translation, built from scratch in PyTorch. Best result: GRU+Attention — ROUGE-1: 0.6309, ROUGE-2: 0.4360.
Fine-tuning T5-small on the CNN/DailyMail dataset for abstractive text summarization using Hugging Face Transformers and PyTorch. Includes dataset preprocessing, training, evaluation with ROUGE metrics, and inference scripts for generating concise news summaries.
To associate your repository with the rouge-evaluation topic, visit your repo's landing page and select "manage topics."