COGS

AbstractNatural language is characterized by compositionality: the meaning of a complex expression is constructed from the meanings of its constituent parts. To facilitate the evaluation of the compositional abilities of …...

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 …...

AbstractWe show how the AM parser, a compositional semantic parser (Groschwitz et al., 2018) can solve compositional generalization on the COGS dataset. It is the first semantic parser that achieves …...

AbstractSeveral studies have reported the inability of Transformer models to generalize compositionally, a key type of generalization in many NLP tasks such as semantic parsing. In this paper we explore …...

AbstractRecent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. In this work, we analyze this behavior of seq2seq models and identify two contributing factors: a …...

AbstractDespite the rising prevalence of neural sequence models, recent empirical evidences suggest their deficiency in compositional generalization. One of the current de-facto solutions to this problem is compositional data augmentation, …...

AbstractIn tasks like semantic parsing, instruction following, and question answering, standard deep networks fail to generalize compositionally from small datasets. Many existing approaches overcome this limitation with model architectures that …...