Conditioning, but on Which Distribution? Grammatical Gender in German Plural Inflection

Kate McCurdy, Adam Lopez, Sharon Goldwater


Abstract
Grammatical gender is a consistent and informative cue to the plural class of German nouns. We find that neural encoder-decoder models learn to rely on this cue to predict plural class, but adult speakers are relatively insensitive to it. This suggests that the neural models are not an effective cognitive model of German plural formation.
Anthology ID:
2020.cmcl-1.8
Volume:
Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics
Month:
November
Year:
2020
Address:
Online
Editors:
Emmanuele Chersoni, Cassandra Jacobs, Yohei Oseki, Laurent Prévot, Enrico Santus
Venue:
CMCL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
59–65
Language:
URL:
https://aclanthology.org/2020.cmcl-1.8
DOI:
10.18653/v1/2020.cmcl-1.8
Bibkey:
Cite (ACL):
Kate McCurdy, Adam Lopez, and Sharon Goldwater. 2020. Conditioning, but on Which Distribution? Grammatical Gender in German Plural Inflection. In Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pages 59–65, Online. Association for Computational Linguistics.
Cite (Informal):
Conditioning, but on Which Distribution? Grammatical Gender in German Plural Inflection (McCurdy et al., CMCL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.cmcl-1.8.pdf