Compositional Generalization via Semantic Tagging

Abstract

Although neural sequence-to-sequence models have been successfully applied to semantic parsing, they fail at compositional generalization, i.e., they are unable to systematically generalize to unseen compositions of seen components. Motivated by traditional semantic parsing where compositionality is explicitly accounted for by symbolic grammars, we propose a new decoding framework that preserves the expressivity and generality of sequence-to-sequence models while featuring 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 meaning of 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 show that the proposed approach consistently improves compositional generalization across model architectures, domains, and semantic formalisms.

arXiv commentEMNLP 2021, Findings

References in corpus (7)

• Sequence to Sequence Learning with Neural Networks
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• The Natural Language Decathlon: Multitask Learning as Question Answering
• Improving Text-to-SQL Evaluation Methodology
• Measuring Compositional Generalization: A Comprehensive Method on Realistic Data
• Towards Universal Semantic Tagging

Cited by in corpus (2)

• Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations
• Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks