Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
Adversarial perturbations of normal images are usually imperceptible to humans, but they can seriously confuse state-of-the-art machine learning models. What makes them so special in the eyes of…
Learning to Automatically Solve Algebra Word Problems
An approach for automatically learning to solve algebra word problems by reasons across sentence boundaries to construct and solve a system of linear equations, while simultaneously recovering an alignment of the variables and numbers to the problem text.
Learning to Solve Arithmetic Word Problems with Verb Categorization
- Mohammad Javad Hosseini, Hannaneh Hajishirzi, Oren Etzioni, Nate Kushman
- Computer ScienceEMNLP
- 1 October 2014
The paper analyzes the arithmetic-word problems “genre”, identifying seven categories of verbs used in such problems, and reports the first learning results on this task without reliance on predefined templates and makes the data publicly available.
Constructing Unrestricted Adversarial Examples with Generative Models
The empirical results on the MNIST, SVHN, and CelebA datasets show that unrestricted adversarial examples can bypass strong adversarial training and certified defense methods designed for traditional adversarial attacks.
R-BGP: Staying Connected in a Connected World
Simulations on the AS-level graph of the current Internet show that R-BGP reduces the number of domains that see transient disconnectivity resulting from a link failure from 22% for edge links and 14% for core links down to zero in both cases.
ZipTx: Harnessing Partial Packets in 802.11 Networks
This paper introduces ZipTx, a software-only solution that harvests the gains from using correct bits in corrupted packets using existing hardware, and characterizes the true gains of partially correct packets for the entire range of operation of 802.11 networks, and in the presence of adaptive modulation and error correcting codes.
Neural Generation of Regular Expressions from Natural Language with Minimal Domain Knowledge
- N. Locascio, Karthik Narasimhan, E. DeLeon, Nate Kushman, R. Barzilay
- Computer ScienceEMNLP
- 9 August 2016
This paper proposes a methodology for collecting a large corpus of regular expression, natural language pairs, and achieves a performance gain of 19.6% over previous state-of-the-art models.
Learning Robust Representations via Multi-View Information Bottleneck
- M. Federici, Anjan Dutta, Patrick Forr'e, Nate Kushman, Zeynep Akata
- Computer ScienceICLR
- 17 February 2020
A theoretical analysis leads to the definition of a new multi-View model which produces state-of-the-art results on two standard multi-view datasets, Sketchy and MIR-Flickr, empirically showing better generalization capabilities when compared to traditional unsupervised approaches.
MAWPS: A Math Word Problem Repository
- Rik Koncel-Kedziorski, Subhro Roy, Aida Amini, Nate Kushman, Hannaneh Hajishirzi
- Computer ScienceNAACL
- 12 June 2016
MAWPS allows for the automatic construction of datasets with particular characteristics, providing tools for tuning the lexical and template overlap of a dataset as well as for filtering ungrammatical problems from web-sourced corpora.
Learning to share: narrowband-friendly wideband networks
This paper presents SWIFT, the first system where high-throughput wideband nodes are shown in a working deployment to coexist with unknown narrowband devices, while forming a network of their own, and implements SWIFT on a wideband hardware platform, and evaluates it in the presence of 802.11 devices.