We present a number of semi-supervised parsing 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.
|Title of host publication||SPMRL 2013|
|Subtitle of host publication||Fourth Workshop on Statistical Parsing of Morphologically Rich Languages : proceedings of the the workshop|
|Place of Publication||Stroudsburg, PA|
|Publisher||Association for Computational Linguistics|
|Number of pages||11|
|Publication status||Published - 2013|
|Event||Workshop on Statistical Parsing of Morphologically Rich Languages (4th : 2013) - Seattle, WA|
Duration: 18 Oct 2013 → 21 Oct 2013
|Workshop||Workshop on Statistical Parsing of Morphologically Rich Languages (4th : 2013)|
|Period||18/10/13 → 21/10/13|
Lynn, T., Foster, J., Dras, M., & van Genabith, J. (2013). Working with a small dataset - semi-supervised dependency parsing for Irish. In SPMRL 2013: Fourth Workshop on Statistical Parsing of Morphologically Rich Languages : proceedings of the the workshop (pp. 1-11). Stroudsburg, PA: Association for Computational Linguistics.