Papers with Kirov

2 papers
Inflecting When There’s No Majority: Limitations of Encoder-Decoder Neural Networks as Cognitive Models for German Plurals (2020.acl-main)

Copied to clipboard

Challenge: Encoder-decoder models can be used to generalize to inflectional morphology and generalize new words, but they fail on tasks like German number inflection, where infrequent suffixes like /-s/ can still be productively generalized.
Approach: They propose to use a dataset to collect data from German speakers to examine whether ED models can generalize the most frequently produced plural class.
Outcome: The proposed model does not show human-like variability or ‘regular’ extension of other plural markers.
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