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.

介绍了针对类似代码生成和语义解析等需要将非结构化（或部分结构化）输入映射到格式化可执行输出的抽象语法网络建模框架，并使用一个具有动态确定模块化结构的解码器构建输出，具有与输出树结构相一致的特性，在 Hearthstone 数据集上获取了 79.2 BLEU 和 22.7% 的精确匹配度，相比之前最先进的值提高了 12.1 和 16.6 个百分点，在 Atis、Jobs 和 Geo 语义解析数据集上的表现也很有竞争力，并且无需进行任何任务特定的工程。