Exploring Methods for Parsing Movie Scripts - Feature Extraction for Further Social Injustice Analysis

Gwilym Newton, Lamogha Chiazor

Keywords: Movie Parsing, Script Parsing, Parsers, IMSDB, Deep Neural Networks, Discussion Tree, BERT Parser

TL;DR: An exploration of methods to parse movie scripts

Abstract: When it comes to analysing movie scripts for things like bias and given the variation of movie script formatting due to inconsistencies by the authors, it is important that we create methods that can help extract all the relevant features required for any further analysis. In this paper, we discuss multiple parsing techniques that can be used to extract features and understand the structure of movie scripts in an automated fashion. We compare and contrast the accuracy and time of a rule based and a variety of machine learning approaches including; Deep Neural Networks, Decision Tress and BERT for sequence classification model.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)