CS Senior Comps

Introduction This project aims to explore the research done on automatic abstract text summarization and look for ways to improve the model. The topic of automatic text summarization was chosen because of my interest in cutting down time spent on reading materials that could be dry and dull on occasions. With the rise of popularity in Neural Networks and my previous knowledge in Machine Learning, I wanted to study and learn more about the development of automatic text summarization tools. While there are two fields of automatic text summarization (extractive and abstractive), I focus on abstractive approaches due to its higher difficulty and significance in creating a human-like summarization tool. Here is a general overview: Existing Work Automatic text summarization is considered a sequence-to-sequence problem (seq2seq); meaning, it's a prediction problem that takes a sequence as input and requires a sequence as output. For seq2seq problems, Recurrent Neural Networks...

Last blog post ended a bit abruptly so let me recap and add onto some things discussed on the last blog post. The two_models branch  utilizes two models: an off-the-shelf Coreference Resolution model  and the Pointer-Generator model . The Coreference Resolution model is used during pre-processing and post-processing of the data. Before the training data is fed into the Pointer-Generator model to train the automatic summarization model, the data goes through the Coreference Resolution model where the model replaces all the pronouns with the noun that the pronouns are referring to  ( e.g.  The text  "Wayne saw himself."  becomes  "Wayne saw Wayne." ) and saves the noun and the pronouns  ( e.g.  { Wayne : [ he, his, him, student ]})  in local storage for later use. The pre-processed model is then used to train the summarization model through the Pointer-Generator model. When the model spits out a summary given an input, it looks for the s...