Despite the ubiquity of ambiguity in natural language, it is often ignor...
We illustrate how a calibrated model can help balance common trade-offs ...
Visual Question Answering (VQA) models often perform poorly on
out-of-di...
Task-oriented semantic parsing is increasingly being used in user-facing...
In natural language understanding (NLU) production systems, users' evolv...
Children acquiring English make systematic errors on subject control
sen...
Our commonsense knowledge about objects includes their typical visual
at...
While neural symbolic methods demonstrate impressive performance in visu...
While numerous attempts have been made to jointly parse syntax and seman...
We introduce a novel paraphrastic augmentation strategy based on
sentenc...
We introduce a transductive model for parsing into Universal Decompositi...
We present the Universal Decompositional Semantics (UDS) dataset (v1.0),...
We introduce a novel discriminative word alignment model, which we integ...