Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
We present a new question set, text corpus, and baselines assembled to encourage AI research in advanced question answering. Together, these constitute the AI2 Reasoning Challenge (ARC), which…
Question Answering as Global Reasoning over Semantic Abstractions
We propose a novel method for exploiting the semantic structure of text to answer multiple-choice questions. The approach is especially suitable for domains that require reasoning over a diverse set…
SciTail: A Textual Entailment Dataset from Science Question Answering
We present a new dataset and model for textual entailment, derived from treating multiple-choice question-answering as an entailment problem. SCITAIL is the first entailment set that is created…
Approximate Inference via Weighted Rademacher Complexity
Rademacher complexity is often used to characterize the learnability of a hypothesis class and is known to be related to the class size. We leverage this observation and introduce a new technique…
Learning Interpretable Spatial Operations in a Rich 3D Blocks World
In this paper, we study the problem of mapping natural language instructions to complex spatial actions in a 3D blocks world. We first introduce a new dataset that pairs complex 3D spatial…
Commonsense Knowledge in Machine Intelligence
There is growing conviction that the future of computing depends on our ability to exploit big data on theWeb to enhance intelligent systems. This includes encyclopedic knowledge for factual…
Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take…
Dynamic Entity Representations in Neural Language Models
Understanding a long document requires tracking how entities are introduced and evolve over time. We present a new type of language model, EntityNLM, that can explicitly model entities, dynamically…
Zero-Shot Activity Recognition with Verb Attribute Induction
In this paper, we investigate large-scale zero-shot activity recognition by modeling the visual and linguistic attributes of action verbs. For example, the verb “salute” has several properties, such…
Learning a Neural Semantic Parser from User Feedback
We present an approach to rapidly and easily build natural language interfaces to databases for new domains, whose performance improves over time based on user feedback, and requires minimal…