Growing trees from morphs: Towards data-driven morphological parsing
- We present a quantitative approach to disambiguating flat morphological analyses and producing more deeply structured analyses. Based on existing morphological segmentations, possible combinations of resulting word trees for the next level are filtered first by criteria of linguistic plausibility and then by weighting procedures based on the geometric mean. The frequencies for weighting are derived from three different sources (counts of morphs in a lexicon, counts of largest constituents in a lexicon, counts of token frequencies in a corpus) and can be used either to find the best analysis on the level of morphs or on the next higher constituent level. The evaluation shows that for this task corpus-based frequency counts are slightly superior to counts of lexical data.
Author: | Petra SteinerORCiD, Josef RuppenhoferGND |
---|---|
URN: | urn:nbn:de:bsz:mh39-52323 |
URL: | http://www.gscl.org/proceedings/2015/ |
Parent Title (English): | Proceedings of the Int. Conference of the German Society for Computational Linguistics and Language Technology, Sep 30–Oct 2 2015 |
Publisher: | Gesellschaft für Sprachtechnologie and Computerlinguistik |
Document Type: | Conference Proceeding |
Language: | English |
Year of first Publication: | 2015 |
Date of Publication (online): | 2016/09/01 |
Publicationstate: | Veröffentlichungsversion |
Reviewstate: | Peer-Review |
Tag: | morphological analyses; word trees |
GND Keyword: | Computerlinguistik; Deutsch; Morphemanalyse; Segmentierung; Worthäufigkeit |
First Page: | 49 |
Last Page: | 57 |
DDC classes: | 400 Sprache / 410 Linguistik |
Open Access?: | ja |
BDSL-Classification: | Textwissenschaft |
Linguistics-Classification: | Computerlinguistik |
Licence (German): | ![]() |