Compositional Generalization via Semantic Tagging

2020/10/22 by Hao Zheng, Mirella Lapata, Zheng, Hao +1 · 3 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2010.11818

openalex publication_date 2020/10/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Long Short-Term Memory
• Sequence to Sequence Learning with Neural Networks
• The Natural Language Decathlon: Multitask Learning as Question Answering

Cited by

• Handling Open-Vocabulary Constructs in Formalizing Specifications: Retrieval-Augmented Parsing with Expert Knowledge
• Compositional Generalisation for Explainable Hate Speech Detection
• Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations

Related

• Compositional Generalization Requires Compositional Parsers
• Learning Algebraic Recombination for Compositional Generalization
• Improving Compositional Generalization with Latent Structure and Data Augmentation
• Disentangled Sequence to Sequence Learning for Compositional Generalization
• Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning