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.
Project 2: Machine Translation – for Udacity Natural Language Processing Nanodegree
This project implements an Automatic Image Captioning model based on encoder-decoder CNN-RNN architecture trained on COCO dataset. Model is able to generate statements about input image.
Build a deep neural network that functions as part of an end-to-end machine translation pipeline. Your completed pipeline will accept English text as input and return the French translation. You’ll be able to explore several recurrent neural network architectures and compare their performance.
Udacity NLP ND: Temporal Deep Neural Networks (Keras RNN variants) for English to French machine translation
The modelling pipeline aims to replicate the translation forum conducted in the imperial courts and the likes of which were rigorously formalised since the times of Dao’an 道安. As described in scholarly texts like translation of T 1543 Abhidharma-jñānaprasthāna-śāstra in 383 AD in Chang’an 長安.
Add a description, image, and links to the encoder-decoder-rnn topic page so that developers can more easily learn about it.
To associate your repository with the encoder-decoder-rnn topic, visit your repo's landing page and select "manage topics."