Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Unsupervised Commonsense Question Answering with Self-Talk
Natural language understanding involves reading between the lines with implicit background knowledge. Current systems either rely on pre-trained language models as the sole implicit source of world…
What-if I ask you to explain: Explaining the effects of perturbations in procedural text
We address the task of explaining the effects of perturbations in procedural text, an important test of process comprehension. Consider a passage describing a rabbit's life-cycle: humans can easily…
Writing Strategies for Science Communication: Data and Computational Analysis
Communicating complex scientific ideas without misleading or overwhelming the public is challenging. While science communication guides exist, they rarely offer empirical evidence for how their…
X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers
Mirroring the success of masked language models, vision-and-language counterparts like VILBERT, LXMERT and UNITER have achieved state of the art performance on a variety of multimodal discriminative…
"You are grounded!": Latent Name Artifacts in Pre-trained Language Models
Pre-trained language models (LMs) may perpetuate biases originating in their training corpus to downstream models. We focus on artifacts associated with the representation of given names (e.g.,…
ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization
We study the problem of recognizing visual entities from the textual descriptions of their classes. Specifically, given birds' images with free-text descriptions of their species, we learn to…
Rearrangement: A Challenge for Embodied AI
We describe a framework for research and evaluation in Embodied AI. Our proposal is based on a canonical task: Rearrangement. A standard task can focus the development of new techniques and serve as…
ABNIRML: Analyzing the Behavior of Neural IR Models
Numerous studies have demonstrated the effectiveness of pretrained contextualized language models such as BERT and T5 for ad-hoc search. However, it is not wellunderstood why these methods are so…
GO FIGURE: A Meta Evaluation of Factuality in Summarization
Text generation models can generate factually inconsistent text containing distorted or fabricated facts about the source text. Recent work has focused on building evaluation models to verify the…
NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints
Conditional text generation often requires lexical constraints, i.e., which words should or shouldn’t be included in the output text. While the dominant recipe for conditional text generation has…