arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.08768cs.CL
收藏

约束语言模型产生Few-Shot语义分析器

Constrained Language Models Yield Few-Shot Semantic Parsers

Microsoft Semantic Machines(微软语义机器)

Richard Shin, Christopher H. Lin, Sam Thomson, Charles Chen, Subhro Roy, Emmanouil Antonios Platanios, Adam Pauls, Dan Klein, Jason Eisner, Benjamin Van Durme

摘要:

我们探索使用大型预训练语言模型作为Few-Shot语义解析器。语义解析的目标是在给定自然语言输入的情况下生成结构化的含义表示。然而,语言模型被训练以生成自然语言。为了弥合这一差距,我们使用语言模型将输入解释为类似英语的受控子语言,该子语言可以自动映射到目标含义表示。我们的研究结果表明,只有少量的数据和很少的代码转换成类似英语的表示,我们的快速引导语义解析器的蓝图在多个社区任务上产生了令人惊讶的有效性能,大大超过了在相同的有限数据上训练的基线方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑