Arrieta, K. and Fillottrani, P. R. and Keet, C.M. (2024) CoSMo: A multilingual modular language for Content Selection Modelling, Proceedings of The 39th ACM/SIGAPP Symposium On Applied Computing (SAC'24), 8-12 April 2024, Avial, Spain, 706-713, ACM.
![[thumbnail of CoSMoSAC24CRC.pdf]](https://pubs.cs.uct.ac.za/style/images/fileicons/text.png) |
Text
CoSMoSAC24CRC.pdf Download (662kB) |
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 Content Selection Modeling 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.
| Item Type: | Conference paper |
|---|---|
| Subjects: | Information systems > Data management systems > Query languages Software and its engineering > Software notations and tools > System description languages > System modeling languages |
| Alternate Locations: | https://dl.acm.org/doi/10.1145/3605098.3635889 |
| Date Deposited: | 10 Aug 2024 13:30 |
| Last Modified: | 10 Aug 2024 13:30 |
| URI: | https://pubs.cs.uct.ac.za/id/eprint/1682 |
Actions (login required)
 |
View Item |