SPECITELLER -- an NLP Tool developed at UPenn

Specificity is an important characterization of texts potentially beneficial for a range of applications such as multi-document news summarization and analysis of science journalism. In this talk we present SPECITELLER, a practical system for predicting sentence specificity which exploits only features that require minimum processing and is trained in a semi-supervised manner. Our system outperforms the state-of-the-art method and does not require part of speech tagging or syntactic parsing as the prior methods did. Using SPECITELLER, we also present our study in the role of specificity in sentence simplification. We show that specificity is a useful indicator for finding sentences that need to be simplified and a useful objective for simplification, descriptive of the differences between original and simplified sentences.

About the Speaker:

J. Jessy Li is a 4th year PhD student working with Dr. Ani Nenkova at the University of Pennsylvania. Her research interests are in natural language processing with focus on discourse processing. In particular she is interested in analyzing and accounting for the variability of discourse and information organization in text.