Towards Synthesizing Complex Programs From Input-Output Examples

61 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Neural Logic Machines (2019, background): “In Chen et al. (2018), more complex programs such as language parsing are studied.”
AutoML-Zero: Evolving Machine Learning Algorithms From Scratch (2020, background): “program parsing [14], and game playing [89], to name a few.”
Tree-to-tree Neural Networks for Program Translation (2018, background): “Other work study using neural networks to generate parse trees from input-output examples [11, 31, 1, 26, 32, 3, 12, 8, 7].”
Compositional Generalization by Learning Analytical Expressions (2020, background): “Besides, as done in literature [7], we accumulate training data from previous lessons to avoid catastrophic forgetting.”
Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs (2018, methodology): “We took inspiration from the recent work (33) in bringing the machine itself into program synthesis.”
Execution-Guided Neural Program Synthesis (2018, methodology): “We follow the literature (Devlin et al., 2017b; Bunel et al., 2018; Chen et al., 2018) to formally define the input-output program synthesis problem below.”
Compositional Generalization via Neural-Symbolic Stack Machines (2020, methodology): “Finally we evaluate NeSS on the context-free grammar parsing tasks in [8].”