Differentiable Tree Operations Promote Compositional Generalization
In the context of structure-to-structure transformation tasks, learning sequences of discrete symbolic operations poses significant challenges due to their non-differentiability. To facilitate the learning of these symbolic sequences, we introduce a differentiable tree interpreter that compiles high-level symbolic tree operations into subsymbolic matrix operations on tensors. We present a novel Differentiable Tree Machine (DTM) architecture that integrates our interpreter with an external memory and an agent that learns to sequentially select tree operations to execute the target transformation in an end-to-end manner. With respect to out-of-distribution compositional generalization on synthetic semantic parsing and language generation tasks, DTM achieves 100% while existing baselines such as Transformer, Tree Transformer, LSTM, and Tree2Tree LSTM achieve less than 30%. DTM remains highly interpretable in addition to its perfect performance.
Code (1)
Tasks
Semantic ParsingText GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Compositional Generalization with Tree Stack Memory Units
We study compositional generalization, viz., the problem of zero-shot generalization to novel compositions of concepts in a domain. Standard neural networks fail to a large extent on compositional learning. We propose Tr…
Mathematical ReasoningZero-shot GeneralizationCompositional Generalization Across Distributional Shifts with Sparse Tree Operations
Neural networks continue to struggle with compositional generalization, and this issue is exacerbated by a lack of massive pre-training. One successful approach for developing neural systems which exhibit human-like comp…
NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalization
Compositional generalization is crucial for artificial intelligence agents to solve complex vision-language reasoning tasks. Neuro-symbolic approaches have demonstrated promise in capturing compositional structures, but …
Compositional Generalization (AVG)Novel ConceptsVisual Question AnsweringVisual Question Answering (VQA)+2Toward 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)Span-based Semantic Parsing for Compositional Generalization
Despite the success of sequence-to-sequence (seq2seq) models in semantic parsing, recent work has shown that they fail in compositional generalization, i.e., the ability to generalize to new structures built of component…
Semantic Parsing