Нейросимволические модели

method ID: neurosymbolicmodels

Related Papers

Structural generalization is hard for sequence-to-sequence models

Authors: nan

Publication: TIPSTER (2022)

DOI: nan

AbstractSequence-to-sequence (seq2seq) models have been successful across many NLP tasks,including ones that require predicting linguistic structure. However, recent work on compositional generalization has shown that seq2seq models achieve very low …...

30870