Reading comprehension (RC) is the to read text, process it, and its meaning. There are two types of summarization: extractive and abstractive. Extractive summarization identifies text and throws away the rest, leaving the passage shorter. Depending on the implementation, it can sound weird and disjointed since text is plucked from different paragraphs. Abstractive summarization is a lot more and it requires the model to understand the text and language in more depth. In the following recipe, we will implement a text summarization algorithm with the TensorFlow framework.
- We start by loading all the libraries, as follows:
import numpy as np import tensorflow as tf
- First, we load the text data:
article_filename = 'Data/summary/"Data/sumdata/train/train.article.txt' title_filename = 'Data/summary/"Data/sumdata/train/train.title.txt' with open(article_filename) as article_file: articles = article_file.readlines() with open(title_filename) as title_file: titles...