Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
QASC: A Dataset for Question Answering via Sentence Composition
Composing knowledge from multiple pieces of texts is a key challenge in multi-hop question answering. We present a multi-hop reasoning dataset, Question Answering via Sentence Composition (QASC),…
On the Capabilities and Limitations of Reasoning for Natural Language Understanding
Recent systems for natural language understanding are strong at overcoming linguistic variability for lookup style reasoning. Yet, their accuracy drops dramatically as the number of reasoning steps…
Expanding Holographic Embeddings for Knowledge Completion
Neural models operating over structured spaces such as knowledge graphs require a continuous embedding of the discrete elements of this space (such as entities) as well as the relationships between…
Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing
This paper presents Memory Augmented Policy Optimization (MAPO): a novel policy optimization formulation that incorporates a memory buffer of promising trajectories to reduce the variance of policy…
Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction
Machine understanding of complex images is a key goal of artificial intelligence. One challenge underlying this task is that visual scenes contain multiple inter-related objects, and that global…
EARLY FUSION for Goal Directed Robotic Vision
Building perceptual systems for robotics which perform well under tight computational budgets requires novel architectures which rethink the traditional computer vision pipeline. Modern vision…
Bridging Knowledge Gaps in Neural Entailment via Symbolic Models
Most textual entailment models focus on lexical gaps between the premise text and the hypothesis, but rarely on knowledge gaps. We focus on filling these knowledge gaps in the Science Entailment…
Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
We present a new kind of question answering dataset, OpenBookQA, modeled after open book exams for assessing human understanding of a subject. The open book that comes with our questions is a set of…
Dissecting Contextual Word Embeddings: Architecture and Representation
Contextual word representations derived from pre-trained bidirectional language models (biLMs) have recently been shown to provide significant improvements to the state of the art for a wide range…
Rational Recurrences
Despite the tremendous empirical success of neural models in natural language processing, many of them lack the strong intuitions that accompany classical machine learning approaches. Recently,…