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 present a novel model to represent and assess the discourse coherence of text. Our model assumes that coherent text implicitly favors certain types of discourse relation transi...
It is well known that parsing accuracy suffers when a model is applied to out-of-domain data. It is also known that the most beneficial data to parse a given domain is data that ...
e evlute severl populr models of lol disourse oherene for domin nd tsk genE erlity y pplying them to ht disentngleE mentF sing experiments ...
We describe a new approach to disambiguating semantic frames evoked by lexical predicates previously unseen in a lexicon or annotated data. Our approach makes use of large amounts...
We present a probabilistic topic model for jointly identifying properties and attributes of social media review snippets. Our model simultaneously learns a set of properties of a ...