The main problem of conditional text generation is that it is mainly based on the content of an input set of examples: this leads to little diversification of the generated text. To overcome this shortcoming, we have fine tuned CTRL using three different datasets. The first model has been used as a baseline for comparison, while the other two ha…

Generating Captions for Images using NLP and Bleu metrics.

This repository contains Python scripts to calculate BLEU (Bilingual Evaluation Understudy) scores to assess the quality of automatic translation systems. BLEU scores are a popular metric for measuring how close a model's output is to a reference translation.

A local evaluation suite for Luxembourgish machine translation.