CoSMo: A constructor specification language for Abstract Wikipedia's content selection process
Arrieta, Kutz, Fillottrani, Pablo R., Keet, C. Maria
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Aug-1-2023
- Country:
- Africa
- Niger (0.04)
- South Africa > Western Cape
- Cape Town (0.04)
- Europe
- Greece > Attica
- Athens (0.04)
- Switzerland (0.04)
- United Kingdom > England
- Oxfordshire > Oxford (0.04)
- Greece > Attica
- North America
- Canada > Quebec
- Estrie Region > Sherbrooke (0.04)
- Montreal (0.04)
- United States > California
- Los Angeles County > Los Angeles (0.04)
- San Diego County > San Diego (0.04)
- San Francisco County > San Francisco (0.04)
- Santa Clara County > Palo Alto (0.04)
- Canada > Quebec
- South America > Argentina
- Pampas > Buenos Aires F.D. > Buenos Aires (0.04)
- Africa
- Genre:
- Research Report (0.40)
- Technology: