Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Repurposing Entailment for Multi-Hop Question Answering Tasks
Question Answering (QA) naturally reduces to an entailment problem, namely, verifying whether some text entails the answer to a question. However, for multi-hop QA tasks, which require reasoning…
Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation
Data-to-text generation can be conceptually divided into two parts: ordering and structuring the information (planning), and generating fluent language describing the information (realization).…
Structural Scaffolds for Citation Intent Classification in Scientific Publications
Identifying the intent of a citation in scientific papers (e.g., background information, use of methods, comparing results) is critical for machine reading of individual publications and automated…
Studying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages
How do typological properties such as word order and morphological case marking affect the ability of neural sequence models to acquire the syntax of a language? Cross-linguistic comparisons of…
Text Generation from Knowledge Graphs with Graph Transformers
Generating texts which express complex ideas spanning multiple sentences requires a structured representation of their content (document plan), but these representations are prohibitively expensive…
Value-based Search in Execution Space for Mapping Instructions to Programs
Training models to map natural language instructions to programs given target world supervision only requires searching for good programs at training time. Search is commonly done using beam search…
White-to-Black: Efficient Distillation of Black-Box Adversarial Attacks
We show that a neural network can learn to imitate the optimization process performed by white-box attack in a much more efficient manner. We train a black-box attack through this imitation process…
FlowQA: Grasping Flow in History for Conversational Machine Comprehension
Conversational machine comprehension requires a deep understanding of the conversation history. To enable traditional, single-turn models to encode the history comprehensively, we introduce Flow, a…
Neural network gradient-based learning of black-box function interfaces
Deep neural networks work well at approximating complicated functions when provided with data and trained by gradient descent methods. At the same time, there is a vast amount of existing functions…
Visual Semantic Navigation using Scene Priors
How do humans navigate to target objects in novel scenes? Do we use the semantic/functional priors we have built over years to efficiently search and navigate? For example, to search for mugs, we…