Learning to Search for Dependencies
Computation and Language
2015-05-11 v2 Machine Learning
Abstract
We demonstrate that a dependency parser can be built using a credit assignment compiler which removes the burden of worrying about low-level machine learning details from the parser implementation. The result is a simple parser which robustly applies to many languages that provides similar statistical and computational performance with best-to-date transition-based parsing approaches, while avoiding various downsides including randomization, extra feature requirements, and custom learning algorithms.
Keywords
Cite
@article{arxiv.1503.05615,
title = {Learning to Search for Dependencies},
author = {Kai-Wei Chang and He He and Hal Daumé and John Langford},
journal= {arXiv preprint arXiv:1503.05615},
year = {2015}
}