Title
《How Far are We from Effective Context Modeling? An Exploratory Study on Semantic Parsing in Context》
Abstract
Recently semantic parsing in context has received considerable attention, which is challenging since there are complex contextual phenomena. Previous works verifified their proposed methods in limited scenarios, which motivates us to conduct an exploratory study on context modeling methods under real-world semantic parsing in context. We present a grammar-based decoding semantic parser and adapt typical context modeling methods on top of it. We evaluate 13 context modeling methods on two large complex cross-domain datasets, and our best model achieves state-of-the-art performances on both datasets with signifificant improvements.Furthermore, we summarize the most frequent contextual phenomena, with a fifine-grained analysis on representative models, which may shed light on potential research directions. Our code is available at https://github.com/microsoft/ContextualSP.
上下文语义解析在复杂语境环境中具有挑战性。我们提出了一种基于语法的解码语义解析器，并在此基础上提出上下文建模方法。同时对有代表性的模型进行细粒度分析，探索潜在的研究方向。
Introduction
语义解析是将自然语言的句子转化为对应的可执行逻辑形式（eg:SQL),这样用户就不用学习逻辑形式下背后的技术。先前的
