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

A neural network to generate captions for an image using CNN and RNN with BEAM Search.

A modular library built on top of Keras and TensorFlow to generate a caption in natural language for any input image.

Python code for various NLP metrics

The LSTM model generates captions for the input images after extracting features from pre-trained VGG-16 model. (Computer Vision, NLP, Deep Learning, Python)

A basic AI chat using the OpenAI API and its GPT-3 models

Useful python NLP tools (evaluation, GUI interface, tokenization)

A visual and interactive scoring environment for machine translation systems.

Deep CNN-LSTM for Generating Image Descriptions 😈

To evaluate machine translation, they use several methods, some of which we fully implemented

Scripts for an upcoming blog "Extractive vs. Abstractive Summarization" for RaRe Technologies.

Abstractive text summarization done with the help of LSTMs using encoder-decoder model which was able to achieve accuracy of 77.27% on training set and cumulative BLEU-4 score of 0.8800 on test set.

State of the art of Neural Machine Translation with PyTorch and TorchText.

In this project, I define and train an image-to-caption model that can produce descriptions for real world images with Flickr-8k dataset.

Implementation for paper BLEU: a Method for Automatic Evaluation of Machine Translation

PyTorch implementation of "Attention Is All You Need" by Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin

⚡ Seq2Seq model combines Attention mechanism

Machine learning tools for NLP programming.

Generate caption on images using CNN Encoder- LSTM Decoder structure

BLEU Score in Rust