We describe a question answering model that applies to both images and structured knowledge bases.
State-of-the-art named entity recognition systems rely heavily on hand-crafted features and domain-specific knowledge in order to learn effectively from the small, supervised training corpora that are available.
#18 best model for Named Entity Recognition (NER) on CoNLL 2003 (English)
There is compelling evidence that coreference prediction would benefit from modeling global information about entity-clusters.
In this work, we present a novel counter-fitting method which injects antonymy and synonymy constraints into vector space representations in order to improve the vectors' capability for judging semantic similarity.