Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge
To what extent can a neural network systematically reason over symbolic facts? Evidence suggests that large pre-trained language models (LMs) acquire some reasoning capacity, but this ability is…
Learning About Objects by Learning to Interact with Them
Much of the remarkable progress in computer vision has been focused around fully supervised learning mechanisms relying on highly curated datasets for a variety of tasks. In contrast, humans often…
Green AI
The computations required for deep learning research have been doubling every few months, resulting in an estimated 300,000x increase from 2012 to 2018 [2]. These computations have a surprisingly…
From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project
AI has achieved remarkable mastery over games such as Chess, Go, and Poker, and even Jeopardy!, but the rich variety of standardized exams has remained a landmark challenge. Even in 2016, the best…
Do Neural Language Models Overcome Reporting Bias?
Mining commonsense knowledge from corpora suffers from reporting bias, over-representing the rare at the expense of the trivial (Gordon and Van Durme, 2013). We study to what extent pre-trained…
Mitigating Biases in CORD-19 for Analyzing COVID-19 Literature
On the behest of the Office of Science and Technology Policy in the White House, six institutions, including ours, have created an open research dataset called COVID-19 Research Dataset (CORD-19) to…
Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation
We address whether neural models for Natural Language Inference (NLI) can learn the compositional interactions between lexical entailment and negation, using four methods: the behavioral evaluation…
It's not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT
Recent works have demonstrated that multilingual BERT (mBERT) learns rich cross-lingual representations, that allow for transfer across languages. We study the word-level translation information…
Unsupervised Distillation of Syntactic Information from Contextualized Word Representations
Contextualized word representations, such as ELMo and BERT, were shown to perform well on various semantic and syntactic task. In this work, we tackle the task of unsupervised disentanglement…
PySBD: Pragmatic Sentence Boundary Disambiguation
In this paper, we present a rule-based sentence boundary disambiguation Python package that works out-of-the-box for 22 languages. We aim to provide a realistic segmenter which can provide logical…