Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
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,…
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…
SimpleQuestions Nearly Solved: A New Upperbound and Baseline Approach
The SimpleQuestions dataset is one of the most commonly used benchmarks for studying single-relation factoid questions. In this paper, we present new evidence that this benchmark can be nearly…
Spot the Odd Man Out: Exploring the Associative Power of Lexical Resources
We propose Odd-Man-Out, a novel task which aims to test different properties of word representations. An Odd-Man-Out puzzle is composed of 5 (or more) words, and requires the system to choose the…
Structured Alignment Networks for Matching Sentences
Many tasks in natural language processing involve comparing two sentences to compute some notion of relevance, entailment, or similarity. Typically this comparison is done either at the word level…
SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference
Given a partial description like"she opened the hood of the car,"humans can reason about the situation and anticipate what might come next ("then, she examined the engine"). In this paper, we…
Syntactic Scaffolds for Semantic Structures
We introduce the syntactic scaffold, an approach to incorporating syntactic information into semantic tasks. Syntactic scaffolds avoid expensive syntactic processing at runtime, only making use of a…
Understanding Convolutional Neural Networks for Text Classification
We present an analysis into the inner workings of Convolutional Neural Networks (CNNs) for processing text. CNNs used for computer vision can be interpreted by projecting filters into image space,…
Word Sense Induction with Neural biLM and Symmetric Patterns
An established method for Word Sense Induction (WSI) uses a language model to predict probable substitutes for target words, and induces senses by clustering these resulting substitute vectors. We…
QuAC: Question Answering in Context
We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total). The dialogs involve two crowd workers: (1) a student who…