Current Projects
Related Research


Can we connect images to the nodes of WordNet? See the pictures we've collected.


Li Fei-Fei (*), Kai Li, Jia Deng, Hao Su, Richard Socher
The participants on this project are supported by the Gordon Wu fellowship, ERP and Upton Fellowship, NSF grant CNS-0509447, Google, Intel, Microsoft, and Yahoo


We are working on a system to add a new relationship to WordNet that connects all parts of speech. Our goal is to bootstrap human ratings of evocation to the entirety of WordNet via machine learning.


Jordan Boyd-Graber (*), Christiane Fellbaum, Dan Osherson, Rob Schapire
This work has been supported by the National Science Foundation

Sense Disambiguation

In order to apply WordNet to untagged corpora, techniques must be developed to perform word sense disambiguation (i.e. determine which WordNet synset corresponds to a particular word in the text). We are applying machine learning techniques to effect accurate word sense disambiguation, thereby allowing a variety of NLP techniques which leverage WordNet to be applied to a wide body of corpora.


Dave Blei(*), Miroslav Dudik, Jonathan Chang, Jordan Boyd-Graber, Dan Osherson, Rob Schapire

From WordNet to a Knowledge Base for Question Answering


Christiane Fellbaum(*), Peter Clark (Boeing), Jerry Hobbs (ISI/USC)

Robust Extraction of Meaning


Christiane Fellbaum(*), Chris Manning (Stanford), Andrew Ng (Stanford), Dan Jurafsky (Stanford)

(*) Contact person