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
Hi-index | 0.00 |
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.