Event Description
The Drexel IEEE Graduate Forum invites you to a talk on "Computational Analysis of Writing Style and Text Quality" by Dr. Ani Nenkova.
Abstract
Natural language research is often equated with attempts to derive structure and meaning from unstructured data. Given this focus, computational treatment of style---how information is expressed rather than what information is expressed---has largely remained unexplored.
In this talk I will argue that elements of style such as the redundancy in text, the specificity of text or the degree to which a text is meant to entertain or inform, affect the performance of standard NLP applications. Good approaches to computational style and text quality analysis will be beneficial for such systems, providing high-level semantic representation of the text.
Dr. Nenkova will overview the systems her students have developed to quantify elements of style, including the ability to detect if a text is verbose, if a text is content-dense or if a text is coherent.
Biography
Dr. Ani Nenkova is an associate professor of Computer and Information Science at the University of Pennsylvania. Her main areas of research are automatic text summarization, affect recognition and text style and quality. She obtained her PhD degree in Computer Science from Columbia University and was a postdoctoral fellow at Stanford University before joining UPenn. Dr. Nenkova and her collaborators are recipients of the best student paper award at SIGDial in 2010 and best paper award at EMNLP in 2012. The Penn team co-led by Dr. Nenkova won the audio-visual emotion recognition challenge (AVEC) for word-level prediction in 2012. |
