Papers by Maria Corkery

1 papers
Are we there yet? Encoder-decoder neural networks as cognitive models of English past tense inflection (P19-1)

Copied to clipboard

Challenge: linguistics and cognitive science have long debated the cognitive mechanisms needed to account for the English past tense.
Approach: They propose to use an encoder-decoder model to account for the english past tense . they also show that ED models demonstrate humanlike performance in a nonce-word task .
Outcome: The proposed model is unstable across simulations and does not fit to human data . other neural models might do better, but there is insufficient evidence to claim them .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations