Semantic parsing using hierarchical representations has recently been
proposed for task oriented dialog with promising results [Gupta et al 2018]. In
this paper, we present three different improvements to the model:
contextualized embeddings, ensembling, and pairwise re-ranking based on a
language model. We taxonomize the errors possible for the hierarchical
representation, such as wrong top intent, missing spans or split spans, and
show that the three approaches correct different kinds of errors. The best
model combines the three techniques and gives 6.4% better exact match accuracy
than the state-of-the-art, with an error reduction of 33%, resulting in a new
state-of-the-art result on the Task Oriented Parsing (TOP) dataset.

本文针对基于任务导向的对话提出了基于分层表示的语义分析方法，并通过嵌入上下文、集成学习和基于语言模型的成对重新排名等三种不同的改进方式来优化模型，将可能存在的分层表示错误进行分类，并展示了三种方法分别纠正不同类型的错误，进而通过将三种技术相结合，提高了 6.4％的准确度和 33％的错误率降低，使其在 TOP 数据集上首次实现了最新的状态 - of-the-art 结果。