Learning Algebraic Recombination for Compositional Generalization
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.
Code (2)
Tasks
Semantic ParsingSimilar Papers 제목 키워드 기반
Improving Compositional Generalization with Latent Structure and Data Augmentation
Generic unstructured neural networks have been shown to struggle on out-of-distribution compositional generalization. Compositional data augmentation via example recombination has transferred some prior knowledge about c…
Data AugmentationDiagnosticSemantic ParsingToward Compositional Generalization in Object-Oriented World Modeling
Compositional generalization is a critical ability in learning and decision-making. We focus on the setting of reinforcement learning in object-oriented environments to study compositional generalization in world modelin…
Decision MakingObjectreinforcement-learningReinforcement Learning (RL)Learning to Recombine and Resample Data for Compositional Generalization
Flexible neural sequence models outperform grammar- and automaton-based counterparts on a variety of tasks. However, neural models perform poorly in settings requiring compositional generalization beyond the training dat…
Data AugmentationInstruction FollowingMorphological AnalysisLinguistic generalization and compositionality in modern artificial neural networks
In the last decade, deep artificial neural networks have achieved astounding performance in many natural language processing tasks. Given the high productivity of language, these models must possess effective generalizat…
Systematic GeneralizationInducing Transformer’s Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks
Systematic compositionality is an essential mechanism in human language, allowing the recombination of known parts to create novel expressions. However, existing neural models have been shown to lack this basic ability i…