papers

Publications (18)

cs.CL2019

KERMIT: Generative Insertion-Based Modeling for Sequences

William Chan, Nikita Kitaev, Kelvin Guu +2

We present KERMIT, a simple insertion-based approach to generative modeling for sequences and sequence pairs. KERMIT models the joint distribution and its decompositions (i.e., mar…

cs.CL2017

A Minimal Span-Based Neural Constituency Parser

Mitchell Stern, Jacob Andreas, Dan Klein

In this work, we present a minimal neural model for constituency parsing based on independent scoring of labels and spans. We show that this model is not only compatible with class…

cs.CL2020

Towards End-to-End In-Image Neural Machine Translation

Elman Mansimov, Mitchell Stern, Mia Chen +3

In this paper, we offer a preliminary investigation into the task of in-image machine translation: transforming an image containing text in one language into an image containing th…

cs.CL2017

Effective Inference for Generative Neural Parsing

Mitchell Stern, Daniel Fried, Dan Klein

Generative neural models have recently achieved state-of-the-art results for constituency parsing. However, without a feasible search procedure, their use has so far been limited t…

cs.CL2019

An Empirical Study of Generation Order for Machine Translation

William Chan, Mitchell Stern, Jamie Kiros +1

In this work, we present an empirical study of generation order for machine translation. Building on recent advances in insertion-based modeling, we first introduce a soft order-re…

cs.LG2018

Adafactor: Adaptive Learning Rates with Sublinear Memory Cost

Noam Shazeer, Mitchell Stern

In several recently proposed stochastic optimization methods (e.g. RMSProp, Adam, Adadelta), parameter updates are scaled by the inverse square roots of exponential moving averages…

cs.CL2020

Semantic Scaffolds for Pseudocode-to-Code Generation

Ruiqi Zhong, Mitchell Stern, Dan Klein

We propose a method for program generation based on semantic scaffolds, lightweight structures representing the high-level semantic and syntactic composition of a program. By first…

cs.CL2019

Insertion Transformer: Flexible Sequence Generation via Insertion Operations

Mitchell Stern, William Chan, Jamie Kiros +1

We present the Insertion Transformer, an iterative, partially autoregressive model for sequence generation based on insertion operations. Unlike typical autoregressive models which…

stat.ML2018

Kernel Feature Selection via Conditional Covariance Minimization

Jianbo Chen, Mitchell Stern, Martin J. Wainwright +1

We propose a method for feature selection that employs kernel-based measures of independence to find a subset of covariates that is maximally predictive of the response. Building o…

stat.ML2018

The Marginal Value of Adaptive Gradient Methods in Machine Learning

Ashia C. Wilson, Rebecca Roelofs, Mitchell Stern +2

Adaptive optimization methods, which perform local optimization with a metric constructed from the history of iterates, are becoming increasingly popular for training deep neural n…

cs.CL2017

Improving Neural Parsing by Disentangling Model Combination and Reranking Effects

Daniel Fried, Mitchell Stern, Dan Klein

Recent work has proposed several generative neural models for constituency parsing that achieve state-of-the-art results. Since direct search in these generative models is difficul…

cs.CL2018

What's Going On in Neural Constituency Parsers? An Analysis

David Gaddy, Mitchell Stern, Dan Klein

A number of differences have emerged between modern and classic approaches to constituency parsing in recent years, with structural components like grammars and feature-rich lexico…

cs.LG2020

Insertion-Deletion Transformer

Laura Ruis, Mitchell Stern, Julia Proskurnia +1

We propose the Insertion-Deletion Transformer, a novel transformer-based neural architecture and training method for sequence generation. The model consists of two phases that are…

cs.GT2021

Dynamic Posted-Price Mechanisms for the Blockchain Transaction Fee Market

Matheus V. X. Ferreira, Daniel J. Moroz, David C. Parkes +1

In recent years, prominent blockchain systems such as Bitcoin and Ethereum have experienced explosive growth in transaction volume, leading to frequent surges in demand for limited…

cs.LG2018

Blockwise Parallel Decoding for Deep Autoregressive Models

Mitchell Stern, Noam Shazeer, Jakob Uszkoreit

Deep autoregressive sequence-to-sequence models have demonstrated impressive performance across a wide variety of tasks in recent years. While common architecture classes such as r…

cs.LG2017

Stochastic Cubic Regularization for Fast Nonconvex Optimization

Nilesh Tripuraneni, Mitchell Stern, Chi Jin +2

This paper proposes a stochastic variant of a classic algorithm---the cubic-regularized Newton method [Nesterov and Polyak 2006]. The proposed algorithm efficiently escapes saddle…

cs.CL2021

Imitation Attacks and Defenses for Black-box Machine Translation Systems

Eric Wallace, Mitchell Stern, Dawn Song

Adversaries may look to steal or attack black-box NLP systems, either for financial gain or to exploit model errors. One setting of particular interest is machine translation (MT),…

cs.CL2017

Abstract Syntax Networks for Code Generation and Semantic Parsing

Maxim Rabinovich, Mitchell Stern, Dan Klein

Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax netwo…