Dissertation Defense
In Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy
Suraj Maharjan
will defend his dissertation
Stylistically Aware Representations of Books
Abstract
Capturing style, a conscious or unconscious choice made by authors to use some form constantly over other possible forms, embedded in documents has a wide range of applications across many domains. In this thesis, we propose a multitude of hand-engineered lexical, syntactic, and stylistic features together with automatic feature learning methods using deep learning to capture different stylistic markers embedded in documents. The methods are general enough to be applied to any domain. However, we chose to evaluate on an interesting and important domain of books. The deeper study of these variations will reveal the dos and don'ts, which might help the authors in shaping their writings. Stylistic analysis helps readers discover new books suited to their taste. We empirically show that traditional hand-engineered features and deep learning methods capture complementary information which upon careful combination yield better performance. Moreover, we find that adding genre classification as an auxiliary task to the primary task of success prediction improves results. Next, we propose a novel multimodal neural architecture that incorporates genre supervision to assign weights to individual feature types. As compared to previous ad-hoc feature combinations, which is time consuming and rigid, this method is capable of dynamically tailoring weights given to feature types based on the characteristics of each book. We then explore the authors' dexterity in use of emotion flow across entire books to captivate readers. We show that modeling the sequential flow of emotions depicted across entire book performs better than without taking this information into account. Finally, we propose a novel method to learn stylistically aware embeddings for authors by feeding in the stylistic traits from their writings. These embeddings also prove to be assets in predicting likability of books.
Date: Wednesday, April 18, 2018
Time: 10:00 AM
Place: PGH 501D
Advisor: Dr. Thamar Solorio
Faculty, students, and the general public are invited.