Macquarie University
01whole.pdf (1.89 MB)

Query-oriented single-document summarization using unsupervised deep learning

Download (1.89 MB)
posted on 2022-03-28, 10:35 authored by Mahmood Yousefiazar
Over the past half a century, machine-based text summarization has been addressed from many different perspectives in a variety of application domains. Deep neural networks recently show promising results for text summarization and this thesis explores this application domain. In this research study, a deep auto-encoder is used to rank sentences based on the most salient information. More precisely, a deep neural network has been used for extractive query-oriented single-document summarization. Also, the use of an Ensemble Noisy Auto-Encoder (ENAE) for this task has been evaluated. ENAE is a stochastic version of an auto-encoder that adds noise to the input text and selects the top sentences from an ensemble of runs. Our experiments show that although a deep auto-encoder can be an effective summarizer, deep auto-encoders trained with stochastic noise in the input and run multiple times with different noise in the input can make improvements. The architecture of ENAE changes the application of the auto-encoder from a deterministic feed-forward network to a stochastic model. To cover a wide range of topics and structures, we perform experiments on two different publicly available email corpora that are specifically designed for text summarization.


Table of Contents

1. Introduction -- 2. Related work -- 3. The methods and algorithms of the architecture -- 4. Results and discussion -- 5. Conclusion and future work.


Empirical thesis. Bibliography: pages 53-59

Awarding Institution

Macquarie University

Degree Type

Thesis MRes


MRes, Macquarie University, Faculty of Science and Engineering, Department of Computing

Department, Centre or School

Department of Computing

Year of Award


Principal Supervisor

Leonard G. C. Hamey

Additional Supervisor 1

Mark Dras


Copyright Mahmood Yousefiazar 2015. Copyright disclaimer:




1 online resource (viii, 64 pages) diagrams, graphs, tables

Former Identifiers