A Self-Evaluating Architecture for Describing Data

Abstract

This paper introduces Linguoplotter, a workspace-based architecture for generating short natural language descriptions. All processes within Linguoplotter are carried out by codelets, small pieces of code each responsible for making incremental changes to the program’s state, the idea of which is borrowed from Hofstadter et al. [6]. Codelets in Linguoplotter gradually transform a representation of temperatures on a map into a description which can be output. Many processes emerge in the program out of the actions of many codelets, including language generation, self-evaluation, and higher-level decisions such as when to stop a given process, and when to end all processing and publish a final text. The program outputs a piece of text along with a satisfaction score indicating how good the program judges the text to be. The iteration of the program described in this paper is capable of linguistically more diverse outputs than a previous version; human judges rate the outputs of this version more highly than those of the last; and there is some correlation between rankings by human judges and the program’s own satisfaction score. But, the program still publishes disappointingly short and simple texts (despite being capable of longer, more complete descriptions). This paper describes: the workings of the program; a recent evaluation of its performance; and possible improvements for a future iteration.

The authors were partially supported by the UK EPSRC under grants EP/R513106/1 (Wright) and EP/S033564/1 (Sodestream: Streamlining Social Decision Making for Improved Internet Standards).