You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The goal of the project is to generate a short and concise summary that captures the salient ideas of the source text using attention model. The generated summaries potentially contain new phrases and sentences that may not appear in the source text
Using a deep learning model that takes advantage of LSTM and a custom Attention layer, we create an algorithm that is able to train on reviews and existent summaries to churn out and generate brand new summaries of its own.
Abstractive text summarization models having encoder decoder architecture built using just LSTMs, Bidirectional LSTMs and Hybrid architecture and trained on TPU. Also pre-trained word embedding is used to speed up the process.