papers AI Learner
The Github is limit! Click to go to the new site.

CNNs found to jump around more skillfully than RNNs: Compositional generalization in seq2seq convolutional networks

2019-05-21
Roberto Dessì, Marco Baroni

Abstract

Lake and Baroni (2018) introduced the SCAN dataset probing the ability of seq2seq models to capture compositional generalizations, such as inferring the meaning of “jump around” 0-shot from the component words. Recurrent networks (RNNs) were found to completely fail the most challenging generalization cases. We test here a convolutional network (CNN) on these tasks, reporting hugely improved performance with respect to RNNs. Despite the big improvement, the CNN has however not induced systematic rules, suggesting that the difference between compositional and non-compositional behaviour is not clear-cut.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.08527

PDF

http://arxiv.org/pdf/1905.08527


Similar Posts

Comments