Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
DeLighT: Deep and Light-weight Transformer
We introduce a very deep and light-weight transformer, DeLighT, that delivers similar or better performance than transformer-based models with significantly fewer parameters. DeLighT more…
MULTIMODALQA: COMPLEX QUESTION ANSWERING OVER TEXT, TABLES AND IMAGES
When answering complex questions, people can seamlessly combine information from visual, textual and tabular sources. While interest in models that reason over multiple pieces of evidence has surged…
Pushing it out of the Way: Interactive Visual Navigation
We have observed significant progress in visual navigation for embodied agents. A common assumption in studying visual navigation is that the environments are static; this is a limiting assumption.…
CODE: COMPILER-BASED NEURON-AWARE ENSEMBLE TRAINING
Deep Neural Networks (DNNs) are redefining the state-of-the-art performance in a variety of tasks like speech recognition and image classification. These impressive results are often enabled by…
Searching for Scientific Evidence in a Pandemic: An Overview of TREC-COVID
We present an overview of the TREC-COVID Challenge, an information retrieval (IR) shared task to evaluate search on scientific literature related to COVID-19. The goals of TREC-COVID include the…
Improving the Accessibility of Scientific Documents: Current State, User Needs, and a System Solution to Enhance Scientific PDF Accessibility for Blind and Low Vision Users
The majority of scientific papers are distributed in PDF, which pose challenges for accessibility, especially for blind and low vision (BLV) readers. We characterize the scope of this problem by…
ManipulaTHOR: A Framework for Visual Object Manipulation
The domain of Embodied AI has recently witnessed substantial progress, particularly in navigating agents within their environments. These early successes have laid the building blocks for the…
BERTese: Learning to Speak to BERT
Large pre-trained language models have been shown to encode large amounts of world and commonsense knowledge in their parameters, leading to substantial interest in methods for extracting that…
Bootstrapping Relation Extractors using Syntactic Search by Examples
The advent of neural-networks in NLP brought with it substantial improvements in supervised relation extraction. However, obtaining a sufficient quantity of training data remains a key challenge. In…
Challenges in Algorithmic Debiasing for Toxic Language Detection
Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently…