Timezone: »

Learned Prioritization for Trading Off Accuracy and Speed
Jiarong Jiang · Adam Teichert · Hal Daumé III · Jason Eisner

Mon Dec 03 07:00 PM -- 12:00 AM (PST) @ Harrah’s Special Events Center 2nd Floor

Users want natural language processing (NLP) systems to be both fast and accurate, but quality often comes at the cost of speed. The field has been manually exploring various speed-accuracy tradeoffs (for particular problems and datasets). We aim to explore this space automatically, focusing here on the case of agenda-based syntactic parsing \cite{kay-1986}. Unfortunately, off-the-shelf reinforcement learning techniques fail to learn good policies: the state space is simply too large to explore naively. An attempt to counteract this by applying imitation learning algorithms also fails: the ``teacher'' is far too good to successfully imitate with our inexpensive features. Moreover, it is not specifically tuned for the known reward function. We propose a hybrid reinforcement/apprenticeship learning algorithm that, even with only a few inexpensive features, can automatically learn weights that achieve competitive accuracies at significant improvements in speed over state-of-the-art baselines.

Author Information

Jiarong Jiang (Two Sigma Investments LP)
Adam Teichert (Johns Hopkins University)
Hal Daumé III (University of Maryland - College Park)
Jason Eisner (Johns Hopkins + Microsoft)

Jason Eisner is Professor of Computer Science at Johns Hopkins University, as well as Director of Research at Microsoft Semantic Machines. He is a Fellow of the Association for Computational Linguistics. At Johns Hopkins, he is also affiliated with the Center for Language and Speech Processing, the Machine Learning Group, the Cognitive Science Department, and the national Center of Excellence in Human Language Technology. His goal is to develop the probabilistic modeling, inference, and learning techniques needed for a unified model of all kinds of linguistic structure. His 135+ papers have presented various algorithms for parsing, machine translation, and weighted finite-state machines; formalizations, algorithms, theorems, and empirical results in computational phonology; and unsupervised or semi-supervised learning methods for syntax, morphology, and word-sense disambiguation. He is also the lead designer of Dyna, a new declarative programming language that provides an infrastructure for AI research. He has received two school-wide awards for excellence in teaching, as well as recent Best Paper Awards at ACL 2017 and EMNLP 2019.

More from the Same Authors