Parsing German: How Much Morphology Do We Need?
- We investigate how the granularity of POS tags influences POS tagging, and furthermore, how POS tagging performance relates to parsing results. For this, we use the standard “pipeline” approach, in which a parser builds its output on previously tagged input. The experiments are performed on two German treebanks, using three POS tagsets of different granularity, and six different POS taggers, together with the Berkeley parser. Our findings show that less granularity of the POS tagset leads to better tagging results. However, both too coarse-grained and too fine-grained distinctions on POS level decrease parsing performance.
Download full text files
Additional Services
Statistics
| Author: | Wolfgang Maier, Sandra Kübler, Daniel Dakota, Daniel Whyatt |
|---|---|
| URN: | urn:nbn:de:bsz:mh39-61889 |
| URL: | http://www.spmrl.org/category/spmrl-sancl2014.html |
| Parent Title (English): | First Joint Workshop on Statistical Parsing of Morphologically Rich Languages and Syntactic Analysis of Non-Canonical Language (SPMRL-SANCL 2014). August 2014. Dublin, Ireland |
| Document Type: | Conference Proceeding |
| Language: | English |
| Year of first Publication: | 2014 |
| Date of Publication (online): | 2017/05/23 |
| Publicationstate: | Veröffentlichungsversion |
| Reviewstate: | Peer-Review |
| Tag: | German; morphology; part-of-speech (POS) |
| GND Keyword: | Deutsch; Morphologie <Linguistik>; Syntaktische Analyse |
| First Page: | 1 |
| Last Page: | 14 |
| DDC classes: | 400 Sprache / 400 Sprache, Linguistik |
| Open Access?: | ja |
| BDSL-Classification: | Grammatik |
| Linguistics-Classification: | Korpuslinguistik |
| Linguistics-Classification: | Morphologie |
| Licence (English): |  Creative Commons - Attribution 4.0 International |