Mono- and Cross-Lingual Paraphrased Text Reuse and Extrinsic Plagiarism Detection Muhammad Sharjeel School of Computing and Communications, Lancaster University Supervisors: Dr. Paul Rayson Dr. Rao Muhammad Adeel Nawab Lancaster University, COMSATS University Islamabad, Lancaster, United Kingdom Lahore Campus, Pakistan
[email protected] [email protected] A dissertation submitted in fulfilment of the requirements for the degree of Doctor of Philosophy in Computer Science June 23, 2020 This thesis is dedicated to my mother, and my late father. Acknowledgements In the Name of Allah, the Most Gracious, the Most Merciful First and foremost, I thank the Almighty Allah (SWT), the ultimate source of all knowledge and wisdom in this world, for His countless blessings on me. Regarding my dissertation, I would like to express my sincere gratitude towards my thesis supervisors, Dr. Paul Rayson and Dr. Rao Muhammad Adeel Nawab. And I wish to “reuse” this sentence in so many ways, to show how grateful I am for their guidance, continuous motivation, and outstanding support that formed an endless “corpus” of wisdom that will be with me, always! I greatly admire Dr. Paul Rayson for being a kind, accessible, and an amiable supervisor. I am indebted to Dr. Rao Muhammad Adeel Nawab for mentoring my research for the past several years and helping me to develop a strong background in Natural Language Processing and Machine Learning. A thanks also goes to all the anonymous reviewers for their invaluable feedback that has led to significant improvements in my PhD study. A heartfelt thanks goes to my parents! Words cannot express my feelings, espe- cially towards my mother.