no code implementations • LREC 2020 • Ramon Maldonado, S Harabagiu, a
By exemplifying a self-attention joint-learning to predict similar annotations in the EEG report corpus, we discuss the promising results, hoping that our effort will inform the design of novel knowledge capture techniques that will include the language of brain signals.
no code implementations • LREC 2016 • Travis Goodwin, S Harabagiu, a
Building a knowledge graph for representing common-sense knowledge in which concepts discerned from noun phrases are cast as vertices and lexicalized relations are cast as edges leads to learning the embeddings of common-sense knowledge accounting for semantic compositionality as well as implied knowledge.
no code implementations • LREC 2014 • Travis Goodwin, S Harabagiu, a
To perform inference on the graphical model, we describe a technique of smoothing the conditional likelihood of medical concepts by their semantically-similar belief values.
no code implementations • LREC 2012 • Kirk Roberts, Travis Goodwin, S Harabagiu, a M.
Events form complex predicate-argument structures that model the participants in the event, their roles, as well as the temporal and spatial grounding.
no code implementations • LREC 2012 • Kirk Roberts, Michael A. Roach, Joseph Johnson, Josh Guthrie, S Harabagiu, a M.
The rise of micro-blogging in recent years has resulted in significant access to emotion-laden text.