Dongyu Lin, Emily Pitler, Dean P. Foster, Lyle H. Ungar
In the past decade, there has been an explosion of interest in using l1-regularization in replace of l0regularization for feature selection. We present results showing that while l1-regularization...
Revisiting Readability: A Unified Framework for Predicting Text Quality (2009)
We combine lexical, syntactic, and discourse features to produce a highly predictive model of human readers ’ judgments of text readability. This is the first study to take into account such a...
Easily Identifiable Discourse Relations (2008)
Pitler, Emily, Raghupathy, Mridhula, Mehta, Hena, Nenkova, Ani, Lee, Alan, Joshi, Aravind K
We present a corpus study of local discourse relations based on the Penn Discourse Tree Bank, a large manually annotated corpus of explicitly or implicitly realized contingency, comparison, temporal...
Easily identifiable discourse relations (2008)
Emily Pitler, Mridhula Raghupathy, Hena Mehta, Ani Nenkova, Alan Lee, Aravind Joshi
We present a corpus study of local discourse relations based on the Penn Discourse Tree Bank, a large manually annotated corpus of explicitly or implicitly realized relations. We show that while...