Optimizing Dependency Parsing Throughput

Albert Weichselbraun, Norman Süsstrunk

2015

Abstract

Dependency parsing is considered a key technology for improving information extraction tasks. Research indicates that dependency parsers spend more than 95% of their total runtime on feature computations. Based on this insight, this paper investigates the potential of improving parsing throughput by designing feature representations which are optimized for combining single features to more complex feature templates and by optimizing parser constraints. Applying these techniques to MDParser increased its throughput four fold, yielding Syntactic Parser, a dependency parser that outperforms comparable approaches by factor 25 to 400.

Paper Citation

in Harvard Style

Weichselbraun A. and Süsstrunk N. (2015). Optimizing Dependency Parsing Throughput . In Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR, (IC3K 2015) ISBN 978-989-758-158-8, pages 511-516. DOI: 10.5220/0005638905110516

in Bibtex Style

@conference{kdir15,
author={Albert Weichselbraun and Norman Süsstrunk},
title={Optimizing Dependency Parsing Throughput},
booktitle={Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR, (IC3K 2015)},
year={2015},
pages={511-516},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005638905110516},
isbn={978-989-758-158-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 1: KDIR, (IC3K 2015)
TI - Optimizing Dependency Parsing Throughput
SN - 978-989-758-158-8
AU - Weichselbraun A.
AU - Süsstrunk N.
PY - 2015
SP - 511
EP - 516
DO - 10.5220/0005638905110516