CoSMo: A constructor specification language for Abstract Wikipedia's content selection process

TL;DR

CoSMo is a newly designed content selection modeling language tailored for Abstract Wikipedia, enabling multilingual, declarative, and class-instance content representation, with promising initial evaluation results.

Contribution

The paper introduces CoSMo, a novel language specifically designed to meet the complex content selection needs of Abstract Wikipedia and similar applications.

Findings

Successfully designed and specified CoSMo language

Preliminary evaluation indicates its effectiveness

Addresses multilingual and declarative content modeling

Abstract

Representing snippets of information abstractly is a task that needs to be performed for various purposes, such as database view specification and the first stage in the natural language generation pipeline for generative AI from structured input, i.e., the content selection stage to determine what needs to be verbalised. For the Abstract Wikipedia project, requirements analysis revealed that such an abstract representation requires multilingual modelling, content selection covering declarative content and functions, and both classes and instances. There is no modelling language that meets either of the three features, let alone a combination. Following a rigorous language design process inclusive of broad stakeholder consultation, we created CoSMo, a novel {\sc Co}ntent {\sc S}election {\sc Mo}deling language that meets these and other requirements so that it may be useful both in Abstract Wikipedia as well as other contexts. We describe the design process, rationale and choices, the specification, and preliminary evaluation of the language.