We present disputant relation-based method for classifying news articles on contentious issues. We observe that the disputants of a contention are an important feature for underst...
We propose a novel unsupervised method for separating out distinct authorial components of a document. In particular, we show that, given a book artificially “munged” from two...
We study the problem of finding the best headdriven parsing strategy for Linear ContextFree Rewriting System productions. A headdriven strategy must begin with a specified right...
Pierluigi Crescenzi, Daniel Gildea, Andrea Marino,...
We investigate the use of textual Internet conversations for detecting questions in spoken conversations. We compare the text-trained model with models trained on manuallylabeled,...
We show that unseen words account for a large part of the translation error when moving to new domains. Using an extension of a recent approach to mining translations from compara...