Structured Data Representation in Natural Language Interfaces
Structured Data Representation in Natural Language Interfaces
复制标题
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Yutong Shao;Arun Kumar;Ndapandula Nakashole
中科院分区：
文献类型：
--
作者：
Yutong Shao;Arun Kumar;Ndapandula Nakashole
自然语言接口（NLI）允许使用人类语言与计算机系统（包括智能手机和机器人）进行交互。与其他类型的界面（如命令行界面（CLI）或图形用户界面（GUI））相比，NLI使更多的人能够访问数据库或API背后的功能，因为它们只需要自然语言的知识。许多NLI应用程序涉及域的结构化数据（例如，例如酒店预订、产品搜索和事实问题回答等应用。因此，为了完全处理用户问题，除了自然语言理解之外，对结构化数据的理解对模型也至关重要。在本文中，我们研究了用于构建自然语言接口（NLI）的神经网络方法，重点是学习结构数据表示，这些数据表示可以推广到训练时看不到的新数据源和模式。具体来说，我们回顾了两个与自然语言接口相关的任务：i）语义解析，我们专注于数据库访问的文本到SQL，以及ii）面向任务的对话系统API访问。我们调查文本到SQL和面向任务的对话任务的代表性方法，专注于表示和合并结构化数据。最后，我们提出了我们的两个原始研究的结构化数据表示方法的NLI，使访问i）数据库，和ii）可视化API。
A Natural Language Interface (NLI) enables the use of human languages to interact with computer systems, including smart phones and robots. Compared to other types of interfaces, such as command line interfaces (CLIs) or graphical user interfaces (GUIs), NLIs stand to enable more people to have access to functionality behind databases or APIs as they only require knowledge of natural languages. Many NLI applications involve structured data for the domain (e.g., applications such as hotel booking, product search, and factual question answering.) Thus, to fully process user questions, in addition to natural language comprehension, understanding of structured data is also crucial for the model. In this paper, we study neural network methods for building Natural Language Interfaces (NLIs) with a focus on learning structure data representations that can generalize to novel data sources and schemata not seen at training time. Specifically, we review two tasks related to natural language interfaces: i) semantic parsing where we focus on text-to-SQL for database access, and ii) task-oriented dialog systems for API access. We survey representative methods for text-to-SQL and task-oriented dialog tasks, focusing on representing and incorporating structured data. Lastly, we present two of our original studies on structured data representation methods for NLIs to enable access to i) databases, and ii) visualization APIs.