We present a simple yet effective unsupervised domain adaptation method that can be generally applied for different NLP tasks. Our method uses unlabeled target domain instances to...
The relationship between context incongruity and sarcasm has been studied in linguistics. We present a computational system that harnesses context incongruity as a basis for sarca...
We present a novel, count-based approach to obtaining inter-lingual word representations based on inverted indexing of Wikipedia. We present experiments applying these representat...