Feature attribution methods have become a staple method to disentangle t...
We investigate different natural language processing (NLP) approaches ba...
This paper describes our two-stage system for the Euphemism Detection sh...
We propose a method to make natural language understanding models more
p...
We propose VALSE (Vision And Language Structured Evaluation), a novel
be...
Hashtag segmentation, also known as hashtag decomposition, is a common s...
We investigate the ability of general-purpose pretrained vision and lang...
Extreme classification tasks are multi-label tasks with an extremely lar...
Many top-performing image captioning models rely solely on object featur...
Datasets (semi-)automatically collected from the web can easily scale to...
We argue that the next frontier in natural language understanding (NLU) ...
Intermediate-task training has been shown to substantially improve pretr...
In this work, we propose to model the interaction between visual and tex...
We introduce a Multi-modal Neural Machine Translation model in which a
d...
We propose a novel discriminative model that learns embeddings from
mult...
We introduce multi-modal, attention-based neural machine translation (NM...