Distinguishing affixoid formations from compounds
- We study German affixoids, a type of morpheme in between affixes and free stems. Several properties have been associated with them – increased productivity; a bleached semantics, which is often evaluative and/or intensifying and thus of relevance to sentiment analysis; and the existence of a free morpheme counterpart – but not been validated empirically. In experiments on a new data set that we make available, we put these key assumptions from the morphological literature to the test and show that despite the fact that affixoids generate many low-frequency formations, we can classify these as affixoid or non-affixoid instances with a best F1-score of 74%.
Author: | Josef RuppenhoferORCiDGND, Michael WiegandORCiDGND, Rebecca WilmORCiDGND, Katja MarkertGND |
---|---|
URN: | urn:nbn:de:bsz:mh39-85002 |
URL: | http://www.aclweb.org/anthology/C18-1325 |
ISBN: | 978-1-948087-50-6 |
Parent Title (English): | Proceedings of the 27th International Conference on Computational Linguistics. August 20-26, 2018 Santa Fe, New Mexico, USA (COLING 2018) |
Publisher: | The Association for Computational Linguistics |
Place of publication: | Stroudsburg PA, USA |
Editor: | Emily M. Bender, Leon Derczynski, Pierre Isabelle |
Document Type: | Part of a Book |
Language: | English |
Year of first Publication: | 2018 |
Date of Publication (online): | 2019/02/19 |
Publicationstate: | Veröffentlichungsversion |
Reviewstate: | Peer-Review |
Tag: | Affixoid; Automatische Sprachverarbeitung; Deutsch; Semantische Analyse |
First Page: | 3853 |
Last Page: | 3865 |
DDC classes: | 400 Sprache / 430 Deutsch |
Open Access?: | ja |
Leibniz-Classification: | Sprache, Linguistik |
Linguistics-Classification: | Computerlinguistik |
Program areas: | Pragmatik |
Program areas: | Digitale Sprachwissenschaft |
Licence (English): | Creative Commons - Attribution 4.0 International |