Conclusion | Table 3: UAS for modified versions of our parsers on validation data. |
Parsing experiments | measured with unlabeled attachment score ( UAS ): the percentage of words with the correct head.8 |
Parsing experiments | Pass = %dependencies surviving the beam in training data, Orac = maximum achievable UAS on validation data, Accl/Acc2 = UAS of Models 1/2 on validation data, and Timel/Time2 = minutes per perceptron training iteration for Models 1/2, averaged over all 10 iterations. |
Parsing experiments | Table 2: UAS of Models 1 and 2 on test data, with relevant results from related work. |
Experiments | We reported the parser quality by the unlabeled attachment score ( UAS ), i.e., the percentage of tokens (excluding all punctuation tokens) with correct HEADs. |
Experiments | The results showed that the reordering features yielded an improvement of 0.53 and 0.58 points ( UAS ) for the first- and second-order models respectively. |
Experiments | In total, we obtained an absolute improvement of 0.88 points ( UAS ) for the first-order model and 1.36 points for the second-order model by adding all the bilingual subtree features. |
Evaluation | For development, we also report unlabeled attachement scores ( UAS ). |
Evaluation | In the rest of table 1, we report the best-performing results for each of the methods,5 providing the number of rules below and above a particular threshold, along with corresponding UAS and LAS values. |
Evaluation | The whole rule and bigram methods reveal greater precision in identifying problematic dependencies, isolating elements with lower UAS and LAS scores than with frequency, along with corresponding greater pre- |