Working with a small dataset - semi-supervised dependency parsing for Irish
Lynn, Teresa, Foster, JenniferORCID: 0000-0002-7789-4853, Dras, MarkORCID: 0000-0001-9908-7182 and van Genabith, JosefORCID: 0000-0003-1322-7944
(2013)
Working with a small dataset - semi-supervised dependency parsing for Irish.
In: Fourth Workshop on Statistical Parsing of Morphologically Rich Languages, 18 Oct 2013, Seattle, WA. USA.
We present a number of semi-supervised pars- ing experiments on the Irish language carried out using a small seed set of manually parsed trees and a larger, yet still relatively small, set of unlabelled sentences. We take two popular dependency parsers – one graph-based and one transition-based – and compare results for both. Results show that using semi- supervised learning in the form of self-training and co-training yields only very modest improvements in parsing accuracy. We also try to use morphological information in a targeted way and fail to see any improvements.