no code implementations • LREC 2022 • Claire Bonial, Austin Blodgett, Taylor Hudson, Stephanie M. Lukin, Jeffrey Micher, Douglas Summers-Stay, Peter Sutor, Clare Voss
We evaluate an annotation schema for labeling logical fallacy types, originally developed for a crowd-sourcing annotation paradigm, now using an annotation paradigm of two trained linguist annotators.
no code implementations • EMNLP (MRQA) 2021 • Douglas Summers-Stay, Claire Bonial, Clare Voss
Generative language models trained on large, diverse corpora can answer questions about a passage by generating the most likely continuation of the passage followed by a question/answer pair.
no code implementations • 22 Aug 2023 • Ahad Shams, Douglas Summers-Stay, Arpan Tripathi, Vsevolod Metelsky, Alexandros Titonis, Karan Malhotra
We introduce Infinitia, a simulation game system that uses generative image and language models at play time to reshape all aspects of the setting and NPCs based on a short description from the player, in a way similar to how settings are created on the fictional Holodeck.
no code implementations • 31 May 2022 • Peter Sutor, Dehao Yuan, Douglas Summers-Stay, Cornelia Fermuller, Yiannis Aloimonos
This process can be performed iteratively and even on single neural networks by instead making a consensus of multiple classification hypervectors.
no code implementations • 24 Sep 2018 • Douglas Summers-Stay, Peter Sutor, Dandan Li
Representing meaning in the form of high dimensional vectors is a common and powerful tool in biologically inspired architectures.
no code implementations • 28 Jun 2018 • Peter Sutor Jr., Douglas Summers-Stay, Yiannis Aloimonos
Semantic vectors are learned from data to express semantic relationships between elements of information, for the purpose of solving and informing downstream tasks.
no code implementations • 11 Jul 2017 • Douglas Summers-Stay
Representing knowledge as high-dimensional vectors in a continuous semantic vector space can help overcome the brittleness and incompleteness of traditional knowledge bases.
no code implementations • 21 Jun 2017 • Douglas Summers-Stay
Texture synthesis has proven successful at imitating a wide variety of textures.
7 code implementations • CVPR 2017 • Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, Devi Parikh
We propose to counter these language priors for the task of Visual Question Answering (VQA) and make vision (the V in VQA) matter!
no code implementations • 13 Jun 2016 • Douglas Summers-Stay, Clare Voss, Taylor Cassidy
The inherent inflexibility and incompleteness of commonsense knowledge bases (KB) has limited their usefulness.
no code implementations • CVPR 2016 • Peng Zhang, Yash Goyal, Douglas Summers-Stay, Dhruv Batra, Devi Parikh
If the concept can be found in the image, the answer to the question is "yes", and otherwise "no".