DeepAI AI Chat
Log In Sign Up

Compositional Generalization via Semantic Tagging

by   Hao Zheng, et al.

Although neural sequence-to-sequence models have been successfully applied to semantic parsing, they struggle to perform well on query-based data splits that require composition generalization, an ability of systematically generalizing to unseen composition of seen components. Motivated by the explicitly built-in compositionality in traditional statistical semantic parsing, we propose a new decoding framework that preserves the expressivity and generality of sequence-to-sequence models while featuring explicit lexicon-style alignments and disentangled information processing. Specifically, we decompose decoding into two phases where an input utterance is first tagged with semantic symbols representing the meanings of its individual words, and then a sequence-to-sequence model is used to predict the final meaning representation conditioning on the utterance and the predicted tag sequence. Experimental results on three semantic parsing datasets with query-based splits show that the proposed approach consistently improves compositional generalization of sequence-to-sequence models across different model architectures, domains and semantic formalisms.


page 1

page 2

page 3

page 4


Disentangled Sequence to Sequence Learning for Compositional Generalization

There is mounting evidence that existing neural network models, in parti...

Span-based Semantic Parsing for Compositional Generalization

Despite the success of sequence-to-sequence (seq2seq) models in semantic...

Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?

Sequence-to-sequence models excel at handling natural language variation...

Structural generalization is hard for sequence-to-sequence models

Sequence-to-sequence (seq2seq) models have been successful across many N...

Semantic Operator Prediction and Applications

In the present paper, semantic parsing challenges are briefly introduced...

Sequence-to-Sequence Networks Learn the Meaning of Reflexive Anaphora

Reflexive anaphora present a challenge for semantic interpretation: thei...

Iterative Utterance Segmentation for Neural Semantic Parsing

Neural semantic parsers usually fail to parse long and complex utterance...