“…In surface realization, the focus has been on filtering a potential set of syntactic forms for a complete utterance using corpus probabilities to filter the possibilities Knight & Hatzivassiloglou, 1995;Langkilde, 1998;Langkilde & Knight, 1998;Varges, 2001), although there has also been research on selection of the form of a nominal expression using a classifier trained on a corpus of nominal expressions (Cheng, Poesio, Henschel, & Mellish, 2001;Poesio, 2000). Classifiers have also been trained on corpora labelled for TOBI accents to predict the appropriate prosody to output; these prosodic predictors have used various types of input features such as rhetorical structure, semantic features and syntactic features (Hitzeman, Black, Taylor, Mellish, & Oberlander, 1998;Pan & McKeown, 1998).…”