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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

There is an ongoing debate on whether neural networks can grasp thequasi-regularities in languages like humans. In a typical quasi-regularitytask, English past tense inflections, the neural network model has long beencriticized that it learns only to generalize the most frequent pattern, but notthe regular pattern, thus can not learn the abstract categories of regular andirregular and is dissimilar to human performance. In this work, we train a setof transformer models with different settings to examine their behavior on thistask. The models achieved high accuracy on unseen regular verbs and someaccuracy on unseen irregular verbs. The models' performance on the regulars isheavily affected by type frequency and ratio but not token frequency and ratio,and vice versa for the irregulars. The different behaviors on the regulars andirregulars suggest that the models have some degree of symbolic learning on theregularity of the verbs. In addition, the models are weakly correlated withhuman behavior on nonce verbs. Although the transformer model exhibits somelevel of learning on the abstract category of verb regularity, its performancedoes not fit human data well, suggesting that it might not be a good cognitivemodel.

How do we get there? Evaluating transformer neural networks as cognitive models for English past tense inflection