Kenton Murray

Kenton Murray

Auto-generated profile, based on publicly available information

Kenton Murray

Department of Computer Science and Engineering University of Notre Dame

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2019
Verified
Conference Paper
Open access
PDF file
KMKenton Murray
Kenton Murray
JKJeffery Kinnison
Jeffery Kinnison
TNToan Q. Nguyen
Toan Q. Nguyen
WSWalter Scheirer
Walter Scheirer
DCDavid Chiang
David Chiang
Kenton Murray, Jeffery Kinnison, Toan Q. Nguyen, Walter Scheirer, David Chiang. Proceedings of the 3rd Workshop on Neural Generation and Translation. 2019.

1 January 2019
Verified
Conference Paper
Open access
PDF file
KMKenton Murray
Kenton Murray
BDBrian DuSell
Brian DuSell
DCDavid Chiang
David Chiang
Kenton Murray, Brian DuSell, David Chiang. Proceedings of the 3rd Workshop on Neural Generation and Translation. 2019.

2 December 2016 in arXiv
Verified
Preprint
Open access
PDF file
KMKenton W. Murray
Kenton W. Murray
JKJayant Krishnamurthy
Jayant Krishnamurthy
We present probabilistic neural programs, a framework for program induction that permits flexible specification of both a computational model and inference algorithm while simultaneously enabling the use of deep neural networks. Probabilistic neural programs combine a computation graph for specifying a neural network with an operator for weighted nondeterministic choice. Thus, a program describes both a collection of decisions as well as the neural network architecture used to make each one. We evaluate our approach on a challenging diagram question answering task where probabilistic neural programs correctly execute nearly twice as many programs as a baseline model.

20 August 2015 in arXiv
Verified
Preprint
Open access
PDF file
KMKenton Murray
Kenton Murray
DCDavid Chiang
David Chiang
Neural networks have been shown to improve performance across a range of natural-language tasks. However, designing and training them can be complicated. Frequently, researchers resort to repeated experimentation to pick optimal settings. In this paper, we address the issue of choosing the correct number of units in hidden layers. We introduce a method for automatically adjusting network size by pruning out hidden units through $\ell_{\infty,1}$ and $\ell_{2,1}$ regularization. We apply this method to language modeling and demonstrate its ability to correctly choose the number of hidden units while maintaining perplexity. We also include these models in a machine translation decoder and show that these smaller neural models maintain the significant improvements of their unpruned versions.

16 October 2019 in arXiv
Verified
Preprint
Open access
PDF file
KMKenton Murray
Kenton Murray
BDBrian DuSell
Brian DuSell
DCDavid Chiang
David Chiang
This paper describes the Notre Dame Natural Language Processing Group's (NDNLP) submission to the WNGT 2019 shared task (Hayashi et al., 2019). We investigated the impact of auto-sizing (Murray and Chiang, 2015; Murray et al., 2019) to the Transformer network (Vaswani et al., 2017) with the goal of substantially reducing the number of parameters in the model. Our method was able to eliminate more than 25% of the model's parameters while suffering a decrease of only 1.1 BLEU.

31 August 2018 in arXiv
Verified
Preprint
Open access
PDF file
KMKenton Murray
Kenton Murray
DCDavid Chiang
David Chiang
We study two problems in neural machine translation (NMT). First, in beam search, whereas a wider beam should in principle help translation, it often hurts NMT. Second, NMT has a tendency to produce translations that are too short. Here, we argue that these problems are closely related and both rooted in label bias. We show that correcting the brevity problem almost eliminates the beam problem; we compare some commonly-used methods for doing this, finding that a simple per-word reward works well; and we introduce a simple and quick way to tune this reward using the perceptron algorithm.