2017/04/25 by Maxim Rabinovich, Rabinovich, Maxim, Mitchell Stern +3 · 38 citations
Computer Science · Mathematics · #Abstract syntax #Abstract syntax tree #Artificial Intelligence (cs.AI) #Artificial intelligence #Benchmark (surveying) #Code (set theory) #Code generation #Computation and Language (cs.CL) #Computer science #Executable #FOS: Computer and information sciences #Key (lock) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Modular design #Natural Language Processing Techniques #Natural language processing #Parsing #Programming language #Semantics (computer science) #Software Engineering Research #Syntax #Task (project management) #Topic Modeling #Tree (set theory) #cs.AI #cs.CL #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1704.07535
published in arXiv (Cornell University) (Cornell University) · ACL 2017. MR and MS contributed equally
arxiv created 2017/04/25 · openalex publication_date 2017/04/25 · arxiv updated 2017/04/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The outputs are represented as abstract syntax trees (ASTs) and constructed by a decoder with a dynamically-determined modular structure paralleling the structure of the output tree. On the benchmark Hearthstone dataset for code generation, our model obtains 79.2 BLEU and 22.7% exact match accuracy, compared to previous state-of-the-art values of 67.1 and 6.1%. Furthermore, we perform competitively on the Atis, Jobs, and Geo semantic parsing datasets with no task-specific engineering.