Are you sure?: confidence in prediction of dependency tree edges

Authors:
Avihai Mejer;Koby Crammer
Affiliations:
Technion-Israel Institute of Technology, Haifa, Israel;Technion-Israel Institute of Technology, Haifa, Israel
Venue:
NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Year:
2012

Citing 3
Cited 1

Non-projective dependency parsing using spanning tree algorithms

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Online Passive-Aggressive Algorithms

The Journal of Machine Learning Research
Confidence in structured-prediction using confidence-weighted models

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing

ReliAble dependency arc recognition

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe and evaluate several methods for estimating the confidence in the per-edge correctness of a predicted dependency parse. We show empirically that the confidence is associated with the probability that an edge is selected correctly and that it can be used to detect incorrect edges very efficiently. We evaluate our methods on parsing text in 14 languages.