Year: 2011
Type: conference-paper
Abstract: We evaluate the statistical dependency parser, Malt, on a new dataset of sentences taken from tweets. We use a version of Malt which is trained on gold standard phrase structure Wall Street Journal (WSJ) trees converted to Stanford labelled dependencies. We observe a drastic drop in performance moving from our in-domain WSJ test set to the new Twitter dataset, much of which has to do with the propagation of part-of-speech tagging er-rors. Retraining Malt on dependency trees produced by a state-of-the-art phrase structure parser, which has it-self been self-trained on Twitter material, results in a significant improvement. We analyse this improvement by examining in detail the effect of the retraining on in-dividual dependency types.
Authors: Foster, Jennifer, Cetinoglu, Ozlem, Wagner, Joachim, Le Roux, Joseph, Hogan, Stephen, Nivre, Joakim, Hogan, Deirdre, van Genabith, Josef
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1586073462
