I am trying to build a model for extractive text summarization using keras sequential layers. I am having a hard time trying to understand how to input my x data. Should it be an array of documents with each document containing an array of sentences? or should I further break it down to each sentence containing an array of words?

The y input is basically a binary classification of each sentence to check whether or not they belong to the summary of the document.

The first layer is an embedding layer and I'm using 100d Glove word embedding.

P.s: I am new to machine learning.


1 Answer 1



I think what you are looking for is an RNN network (Either LSTM or GRU) with the many-to-many topology.


Clearly your input is the sentences (or to be more precise, the an embedding of your sentences, because you cannot feed the raw text to the network). then for each sentence you want to assign a value, which means for n inputs, you need n outputs. This is the many-to-many architecture.

Moreover, you might want to check the Bi-directional LSTM for your study. Not relevant to your question, but worth mentioning.

For more information, refer to this


You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .