Channels Resources Recent Items Reading list HomeRegisterLoginSupportContact

Authors: Matt Hohensee and Emily M. Bender
Details: | Google Scholar CiteSeer X DBLP Database
View PDF
We propose a linguistically motivated set of features to capture morphological agreement and add them to the MSTParser dependency parser. Compared to the built-in morphological feature set, ours is both much smaller and more accurate across a sample of 20 morphologically annotated treebanks. We find increases in accuracy of up to 5.3% absolute. While some of this results from the feature set capturing information unrelated to morphology, there is still significant improvement, up to 4.6% absolute, due to the agreement model.
Item Details
Status: updated [Success]
Update: last updated 06/13/2012, 06:29 PM

2139 users, 707 channels, 351 resources, 60029 items