The named entity disambiguation task is to resolve the many-to-many correspondence between ambiguous names and the unique realworld entity. This task can be modeled as a classifi...
Most information extraction (IE) systems identify facts that are explicitly stated in text. However, in natural language, some facts are implicit, and identifying them requires ...
We show how features can easily be added to standard generative models for unsupervised learning, without requiring complex new training methods. In particular, each component mul...
Taylor Berg-Kirkpatrick, Alexandre Bouchard-C&ocir...
Little is known about the impact of politeness in online communities. This project combines deductive and inductive approaches to automatically model linguistic politeness in onli...
The analysis of reading times can provide insights into the processes that underlie language comprehension, with longer reading times indicating greater cognitive load. There is e...
Jeff Mitchell, Mirella Lapata, Vera Demberg, Frank...