material ID: cfq

Related Papers

The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers

Authors: nan

Publication: TIPSTER (2021)

DOI: nan

AbstractRecently, many datasets have been proposed to test the systematic generalization ability of neural networks. The companion baseline Transformers, typically trained with default hyper-parameters from standard tasks, are shown to …...

32051

Compositional Generalization in Multilingual Semantic Parsing over Wikidata

Authors: nan

Publication: TIPSTER (2022)

DOI: nan

AbstractSemantic parsing (SP) allows humans to leverage vast knowledge resources through natural interaction. However, parsers are mostly designed for and evaluated on English resources, such as CFQ (Keysers et al., …...

26729