Language to Code: Learning Semantic Parsers for If-This-Then-That Recipes
Language to Code: Learning Semantic Parsers for If-This-Then-That Recipes
复制标题
DOI：
10.3115/v1/p15-1085
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
Chris Quirk;R. Mooney;Michel Galley
中科院分区：
文献类型：
--
作者：
Chris Quirk;R. Mooney;Michel Galley
使用自然语言编写程序是计算语言学的试金石问题。我们提出了一种方法，学习将简单的“if-then”规则的自然语言描述映射到可执行代码。通过对大量自然发生的程序（称为“食谱”）及其自然语言描述进行训练和测试，我们展示了有效将语言映射到代码的能力。我们对从普通用户收集的高噪声训练数据进行了多种语义解析方法的比较，发现松散同步系统的性能最佳。
Using natural language to write programs is a touchstone problem for computational linguistics. We present an approach that learns to map natural-language descriptions of simple “if-then” rules to executable code. By training and testing on a large corpus of naturally-occurring programs (called “recipes”) and their natural language descriptions, we demonstrate the ability to effectively map language to code. We compare a number of semantic parsing approaches on the highly noisy training data collected from ordinary users, and find that loosely synchronous systems perform best.