67 citations · 75 across the 8 of their papers we have counts for
Showing 2022Show all
3 papers · 1 filter
cs.CL2022★ 1 cited
Structural generalization is hard for sequence-to-sequence models
Yuekun Yao, Alexander Koller
Sequence-to-sequence (seq2seq) models have been successful across many NLP tasks, including ones that require predicting linguistic structure. However, recent work on compositional…
cs.CL2022
Compositional Generalisation with Structured Reordering and Fertility Layers
Matthias Lindemann, Alexander Koller, Ivan Titov
Seq2seq models have been shown to struggle with compositional generalisation, i.e. generalising to new and potentially more complex structures than seen during training. Taking ins…
cs.CL2022★ 2 cited
Compositional Generalization Requires Compositional Parsers
Pia Weißenhorn, Yuekun Yao, Lucia Donatelli +1
A rapidly growing body of research on compositional generalization investigates the ability of a semantic parser to dynamically recombine linguistic elements seen in training into…