Abstract
This paper presents our preliminary conclusions as part of an ongoing effort to construct a new dependency representation framework for Turkish. We aim for this new framework to accommodate the highly agglutinative morphology of Turkish as well as to allow the annotation of unedited web data, and shape our decisions around these considerations. In this paper, we firstly describe a novel syntactic representation for morphosyntactic sub-word units (namely inflectional groups (IGs) in Turkish) which allows inter-IG relations to be discerned with perfect accuracy without having to hide lexical information. Secondly, we investigate alternative annotation schemes for coordination structures and present a better scheme (nearly 11% increase in recall scores) than the one in Turkish Treebank (Oflazer et al., 2003) for both parsing accuracies and compatibility for colloquial language.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of SPMRL 2013, the 4th Workshop on Statistical Parsing of Morphologically Rich Languages |
| Number of pages | 6 |
| Publisher | The Association for Computational Linguistics |
| Publication date | 18 Oct 2013 |
| Pages | 129-134 |
| ISBN (Electronic) | 978-1-937284-97-8 |
| Publication status | Published - 18 Oct 2013 |
| MoE publication type | A4 Article in conference proceedings |
| Event | The 4th Workshop on Statistical Parsing of Morphologically Rich Languages - Seattle, United States Duration: 18 Oct 2013 → … |