Learning Algebraic Recombination for Compositional Generalization

Abstract

Neural sequence models exhibit limited compositional generalization ability in semantic parsing tasks. Compositional generalization requires algebraic recombination, i.e., dynamically recombining structured expressions in a recursive manner. However, most previous studies mainly concentrate on recombining lexical units, which is an important but not sufficient part of algebraic recombination. In this paper, we propose LeAR, an end-to-end neural model to learn algebraic recombination for compositional generalization. The key insight is to model the semantic parsing task as a homomorphism between a latent syntactic algebra and a semantic algebra, thus encouraging algebraic recombination. Specifically, we learn two modules jointly: a Composer for producing latent syntax, and an Interpreter for assigning semantic operations. Experiments on two realistic and comprehensive compositional generalization benchmarks demonstrate the effectiveness of our model. The source code is publicly available at https://github.com/microsoft/ContextualSP.

arXiv commentACL Findings 2021

References in corpus (18)

• ADADELTA: An Adaptive Learning Rate Method
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Improving Text-to-SQL Evaluation Methodology
• The Evolved Transformer
• The Optimal Reward Baseline for Gradient-Based Reinforcement Learning
• Compositional Semantic Parsing on Semi-Structured Tables
• Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks
• Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures
• Compositional Generalization by Learning Analytical Expressions
• Hierarchical Poset Decoding for Compositional Generalization in Language
• Neural Shuffle-Exchange Networks -- Sequence Processing in O(n log n) Time
• Compositional Generalization for Primitive Substitutions
• Learning to Recombine and Resample Data for Compositional Generalization
• COGS: A Compositional Generalization Challenge Based on Semantic Interpretation
• Compound Probabilistic Context-Free Grammars for Grammar Induction
• Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization
• Sequence-Level Mixed Sample Data Augmentation