160 likes | 179 Views
Learn about linking adjacent words in a classification-based dependency parsing approach. Explore decision lists for German and accuracy levels up to 95% for most languages. Discover challenges with the greedy bottom-up parsing model.
E N D
Dependency Parsing as a Classification Problem Deniz Yuret Koç University İstanbul
Linking Adjacent Words kick the red ball ? ? ?
Linking Adjacent Words kick the red ball
Linking Adjacent Words kick the red ball ? ?
Linking Adjacent Words kick the red ball ? ? ?
Linking Adjacent Words kick the red ball
Linking Adjacent Words kick the red ball ? ? ? ?
Linking Adjacent Words kick the red ball ? ? ?
Linking Adjacent Words kick the red ball ? ?
Linking Adjacent Words kick the red ball
Sample decision list for German • If XL1:postag=APPR Then NONE • If X:postag=ART, Y:postag=NN Then L:NK • If X:postag=APPR Then R:NK • If TRUE Then NONE
Sample decision list for German • If XL1:postag=APPR Then NONE • If X:postag=ART, Y:postag=NN Then L:NK • If X:postag=APPR Then R:NK • If TRUE Then NONE APPR-ART-NN
Contributions • Learning adjacent word dependencies using decision lists and GPA. • Accuracy on adjacent word dependencies between 85%-95% for most languages. • Greedy bottom-up parsing model did not work very well.