Measuring Alignment Bias in Neural Seq2Seq Semantic Parsers. (arXiv:2205.08288v2 [cs.CL] UPDATED)

Prior to deep learning the semantic parsing community has been interested in
understanding and modeling the range of possible word alignments between
natural language sentences and their corresponding meaning representations.
Sequence-to-sequence models changed the research landscape suggesting that we
no longer need to worry about alignments since they can be learned
automatically by means of an attention mechanism. More recently, researchers
have started to question such premise. In this work we investigate whether
seq2seq models can handle both simple and …

alignment arxiv bias semantic seq2seq