Back to Search
Start Over
Going to the Roots of Dependency Parsing.
- Source :
-
Computational Linguistics . Mar2013, Vol. 39 Issue 1, p5-13. 9p. 1 Diagram, 1 Chart. - Publication Year :
- 2013
-
Abstract
- Dependency trees used in syntactic parsing often include a root node representing a dummy word prefixed or suffixed to the sentence, a device that is generally considered a mere technical convenience and is tacitly assumed to have no impact on empirical results. We demonstrate that this assumption is false and that the accuracy of data-driven dependency parsers can in fact be sensitive to the existence and placement of the dummy root node. In particular, we show that a greedy, left-to-right, arc-eager transition-based parser consistently performs worse when the dummy root node is placed at the beginning of the sentence (following the current convention in data-driven dependency parsing) than when it is placed at the end or omitted completely. Control experiments with an arc-standard transition-based parser and an arc-factored graph-based parser reveal no consistent preferences but nevertheless exhibit considerable variation in results depending on root placement. We conclude that the treatment of dummy root nodes in data-driven dependency parsing is an underestimated source of variation in experiments and may also be a parameter worth tuning for some parsers. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 08912017
- Volume :
- 39
- Issue :
- 1
- Database :
- Academic Search Index
- Journal :
- Computational Linguistics
- Publication Type :
- Academic Journal
- Accession number :
- 85865691
- Full Text :
- https://doi.org/10.1162/COLI_a_00132