English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Can artificial neural networks learn to represent inflectional morphology andgeneralize to new words as human speakers do? Kirov and Cotterell (2018) arguethat the answer is yes: modern Encoder-Decoder (ED) architectures learnhuman-like behavior when inflecting English verbs, such as extending theregular past tense form -(e)d to novel words. However, their work does notaddress the criticism raised by Marcus et al. (1995): that neural models maylearn to extend not the regular, but the most frequent class -- and thus failon tasks like German number inflection, where infrequent suffixes like -s canstill be productively generalized.  To investigate this question, we first collect a new dataset from Germanspeakers (production and ratings of plural forms for novel nouns) that isdesigned to avoid sources of information unavailable to the ED model. Thespeaker data show high variability, and two suffixes evince 'regular' behavior,appearing more often with phonologically atypical inputs. Encoder-decodermodels do generalize the most frequently produced plural class, but do not showhuman-like variability or 'regular' extension of these other plural markers. Weconclude that modern neural models may still struggle with minority-classgeneralization.

Inflecting when there's no majority: Limitations of encoder-decoder neural networks as cognitive models for German plurals