Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
QuaRel: A Dataset and Models for Answering Questions about Qualitative Relationships
Many natural language questions require recognizing and reasoning with qualitative relationships (e.g., in science, economics, and medicine), but are challenging to answer with corpus-based methods.…
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…
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…
Reasoning about Actions and State Changes by Injecting Commonsense Knowledge
Comprehending procedural text, e.g., a paragraph describing photosynthesis, requires modeling actions and the state changes they produce, so that questions about entities at different timepoints can…
Adaptive Stratified Sampling for Precision-Recall Estimation
We propose a new algorithm for computing a constant-factor approximation of precision-recall (PR) curves for massive noisy datasets produced by generative models. Assessing validity of items in such…
Adversarial Training for Textual Entailment with Knowledge-Guided Examples
We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided…
Deep Communicating Agents For Abstractive Summarization
We present deep communicating agents in an encoder-decoder architecture to address the challenges of representing a long document for abstractive summarization. With deep communicating agents, the…
Discourse-Aware Neural Rewards For Coherent Text Generation
In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text. In particular, we propose to learn neural rewards to…