SpatialNLI: A Spatial Domain Natural Language Interface to Databases Using Spatial Comprehension论文学习
研究背景
Due to the idiosyncrasy and expressiveness of the spatial semantics, it is unfeasible to adopt general NLI for the spatial domain directly. The challenge of adopting the existing general domain NLI to spatial domain lies to harnessing the expressiveness of spatial semantics. In general, spatial semantic understanding relies heavily on its contextual interpretation. Contextually dependent spatial semantics raises serious challenges for NLI to spatial domain databases.（由于空间语义的特殊性和表达性，直接对空间域采用通用 NLI 是不可行的。 将现有的通用领域 NLI 应用于空间领域的挑战在于利用空间语义的表达能力。 一般来说，空间语义理解在很大程度上依赖于其上下文解释。 上下文相关的空间语义对空间域数据库的 NLI 提出了严峻的挑战。）
系统设计思路
- Inspired by the machine comprehension model, we propose a spatial comprehension model that is able to recognize the meaning of spatial entities based on the semantics of the context. The spatial semantics learned from the spatial comprehension model is then injected to the natural language question to ease the burden of capturing the spatial-specific semantics. With our spatial comprehension model and information injection, our NLI for the spatial domain, named SpatialNLI, uses a sequence-to-sequence (seq2seq) translation to capture the semantic structure of the question and translate it to the corresponding syntax of an executable query accurately.（受机器理解模型的启发，我们提出了一种空间理解模型，该模型能够根据上下文的语义识别空间实体的含义。 然后将从空间理解模型中学到的空间语义注入到自然语言问题中，以减轻捕获特定空间语义的负担。 通过我们的空间理解模型和信息注入，我们用于空间域的 NLI，名为 SpatialNLI，使用序列到序列 (seq2seq) 转换来捕获问题的语义结构并将其准确地转换为可执行查询的相应语法 .）
- Our fundamental strategy is to separate the tasks of NLI into the following two aspects：（我们的基本策略是将 NLI 的任务分为以下两个方面：(1) seq2seq模型学习自然语言问题的语义结构；(2) 外部空间理解模型学习空间问题的空间语义。）
(1) the seq2seq model learns semantic structure of a natural language question
(2) an external spatial comprehension model learns the spatial semantics of a spatial question. - use an external spatial semantic understanding model to enhance the performance of the main seq2seq model.（使用外部空间语义理解模型来增强主seq2seq模型的性能。）
系统工作流程
The workflow of our SpatialNLI involves the following steps:（我们 SpatialNLI 的工作流程包括以下步骤：1.识别NL查询中的歧义空间语义。2.构建一个空间理解模型，能够从语义上理解空间相关问题。3.将从空间理解模型中检索到的空间语义注入问题中。4.将问题“翻译”为结构化查询。5.将注入的符号替换为其原始文本。）
1.Identify ambiguous spatial semantics in the NL query.
2.Build a spatial comprehension model that is able to understand a spatial-related question semantically.
3.Injecting spatial semantics retrieved from the spatial comprehension model into the question.
4.“Translating” the question into a structured query.
5.Replace the symbols injected to their original text.
如何做实验
- To evaluate the effectiveness of our system, we performed an experimental evaluation on dataset Geoquery and Restaurants.（为了评估我们系统的有效性，我们对数据集 Geoquery 和 Restaurants 进行了实验评估。）
- To validate the performance of our system, several ablation experiments were conducted by the removal of (1) Copy Mechanism, (2) Spatial Comprehension Model, (3) Data Augmentation, (4) Type Feeding and (5) Information Injection, respectively.（为了验证我们系统的性能，分别通过去除（1）复制机制，（2）空间理解模型，（3）数据增强，（4）类型馈送和（5）信息注入进行了几次消融实验。）
- We also jointly train both datasets in a shared model compared with separate training. Our experiment results show that a shared model performs better than two separate models.（与单独训练相比，我们还在共享模型中联合训练两个数据集。 我们的实验结果表明，共享模型的性能优于两个单独的模型。）
