Leveraging Language to Learn Program Abstractions and Search Heuristics
Abstract
Inductive program synthesis, or inferring programs from examples of desired behavior, offers a general paradigm for building interpretable, robust, andgeneralizable machine learning systems. Effective program synthesis depends on two key ingredients: a strong library of functions from which to build programs, and an efficient search strategy for finding programs that solve a given task. We introduce LAPS (Language for Abstraction and Program Search), a technique for using natural language annotations to guide joint learning of libraries and neurally-guided search models for synthesis. When integrated into a state-of-the-art library learning system (DreamCoder), LAPS produces higher-quality libraries and improves search efficiency and generalization on three domains – string editing, image composition, and abstract reasoning about scenes – even when no natural language hints are available at test time.
Cite
Text
Wong et al. "Leveraging Language to Learn Program Abstractions and Search Heuristics." International Conference on Machine Learning, 2021.Markdown
[Wong et al. "Leveraging Language to Learn Program Abstractions and Search Heuristics." International Conference on Machine Learning, 2021.](https://mlanthology.org/icml/2021/wong2021icml-leveraging-a/)BibTeX
@inproceedings{wong2021icml-leveraging-a,
title = {{Leveraging Language to Learn Program Abstractions and Search Heuristics}},
author = {Wong, Lionel and Ellis, Kevin M and Tenenbaum, Joshua and Andreas, Jacob},
booktitle = {International Conference on Machine Learning},
year = {2021},
pages = {11193-11204},
volume = {139},
url = {https://mlanthology.org/icml/2021/wong2021icml-leveraging-a/}
}