数据库语义学纲要

数据库语义学(Database Semantics,DBS)将自然语言交流的周期构建为从听觉过渡到思维再过渡到说话,然后从说话返回到听觉的模式(这是一个循环模式)。与真值条件语义学和短语结构语法使用的替换驱动和基于符号的方法不同,数据库语义学是数据驱动的和基于智能代理的。其目的是为具有语言能力的自主机器人提供一种语义学理论。在数据库语义学中,命题是表示内容的,而不是表示真值的(第1—3节)。内容由指称、属性和关系等语义类建立起来,它们由经典的结构语义关系,即函子论元和协调关系串联而成。为了使指称成为一个智能代理内部的认知过程,语言和非语言的内容都使用了相同的计算数据结构和操作种类,而它们之间的主要区别在于是否存在与语言相关的表面值。数据库语义学包括三部分:(i)一个交互界面,(ii)一个存储器,(iii)一个操作组件。交互界面部分在智能的认知与其外部和内部环境之间进行协调,表示为由传感器和激活器提供的原始数据(第4—7节)。智能代理每时每刻的监测数据都被存储在存储器的前端。作为智能代理控制单元的一部分,存储器的这个前端就是执行操作组件程序的位置所在,它是在内容中产生的。

Outline of Database Semantics (DBS)

Database Semantics (DBS) models the cycle of natural language communication as a transition from the hear to the think to the speak and back to the hear mode (turn taking). In contradistinction to the substitution-driven sign-based approaches of truth-conditional semantics and phrase structure grammar, DBS is data-driven and agent-based. The purpose is a theory of semantics for an autonomous robot with language. Propositions are content in DBS, instead of denoting truth values (Sects. 1-3). Content is built from the semantic kinds of referent, property, and relation, which are concatenated by the classical semantic relations of structure, i.e. functor-argument and coordination. To enable reference as an agent-internal cognitive process, language and nonlanguage contents use the same computational data structure and operation kinds, and differ mostly in the presence vs. absence of language-dependent surface values. DBS consists of (i) an interface, (ii) a memory, and (iii) an operation component^①.The interface component mediates between the agent’s cognition and its external and internal environment, represented as raw data provided by sensors and activators (Sects. 4-7). The data of the agent’s moment by moment monitoring are stored at the memory’s now front. As part of the on-board control unit, the now front is the location for performing the procedures of the operation component, resulting in content.