Mitchell Stern

Kernel feature selection via conditional covariance minimization

2017 · Neural Information Processing Systems

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 on past work in kernel dimension reduction, we …

Insertion Transformer: Flexible Sequence Generation via Insertion Operations

2019 · arXiv (Cornell University)

We present the Insertion Transformer, an iterative, partially autoregressive model for sequence generation based on insertion operations. Unlike typical autoregressive models which rely on a fixed, often left-to-right ordering of the output, our approach accommodates …

A Minimal Span-Based Neural Constituency Parser

2017

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 classical dynamic programming techniques, but …