We explore the use of large pretrained language models as few-shot semantic parsers. The goal in semantic parsing is to generate a structured meaning representation given a natural language input. However, language models are trained to generate natural language. To bridge the gap, we use language models to paraphrase inputs into a controlled sublanguage resembling English that can be automatically mapped to a target meaning representation. Our results demonstrate that with only a small amount of data and very little code to convert into English-like representations, our blueprint for rapidly bootstrapping semantic parsers leads to surprisingly effective performance on multiple community tasks, greatly exceeding baseline methods also trained on the same limited data.
翻译:我们探索使用大型预先培训的语言模型作为少见的语义解析器。语义解析的目的是根据自然语言投入产生结构化的含义代表。然而,语言模型经过培训以产生自然语言。为了弥合这一差距,我们使用语言模型将输入的内容转换成一种可自动映射成目标含义表达法的受控的、类似英语的子语言。我们的结果表明,只要少量的数据和极小的代码可以转换成类似英语的表达法,我们的快速拼写语义解析器蓝图就能在多个社区任务上取得令人惊讶的有效表现,大大超过对同样有限数据的培训基准方法。