CoSMo: A constructor specification language for Abstract Wikipedia's content selection process
This addresses the need for a specialized modeling language in the Abstract Wikipedia project and similar contexts, though it appears incremental as it builds on existing content selection concepts.
The authors tackled the lack of a modeling language for abstract information representation in tasks like content selection for generative AI, by creating CoSMo, a novel language that meets requirements such as multilingual modeling and support for declarative content and functions, with preliminary evaluation conducted.
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.