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.
#29 best model for Named Entity Recognition on CoNLL 2003 (English)
Sequence-to-sequence neural network models for generation of conversational responses tend to generate safe, commonplace responses (e. g., "I don't know") regardless of the input.
We describe a question answering model that applies to both images and structured knowledge bases.
Question answering forums are rapidly growing in size with no effective automated ability to refer to and reuse answers already available for previous posted questions.
There is compelling evidence that coreference prediction would benefit from modeling global information about entity-clusters.
#14 best model for Coreference Resolution on OntoNotes
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.