Distinguishing affixoid formations from compounds

Josef Ruppenhofer, Michael Wiegand, Rebecca Wilm, Katja Markert


Abstract
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%.
Anthology ID:
C18-1325
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3853–3865
Language:
URL:
https://aclanthology.org/C18-1325
DOI:
Bibkey:
Cite (ACL):
Josef Ruppenhofer, Michael Wiegand, Rebecca Wilm, and Katja Markert. 2018. Distinguishing affixoid formations from compounds. In Proceedings of the 27th International Conference on Computational Linguistics, pages 3853–3865, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Distinguishing affixoid formations from compounds (Ruppenhofer et al., COLING 2018)
Copy Citation:
PDF:
https://aclanthology.org/C18-1325.pdf
Code
 josefkr/affixoids