A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is
Humans are remarkably flexible when understanding new sentences that include combinations of concepts they have never encountered before. Recent work has shown that while deep networks can mimic some human language abilities when presented with novel sentences, systematic variation uncovers the limitations in the language-understanding abilities of networks. We demonstrate that these limitations can be overcome by addressing the generalization challenges in the gSCAN dataset, which explicitlyarXiv:2008.02742v3 fatcat:ner76upbvzbxjjximwhguopyei