Replication and Generalization of PRECISE
Michael Minock, Nils Everling

TL;DR
This paper replicates and formalizes the PRECISE system, revealing that initial results did not fully replicate but providing a clearer framework for future improvements and extensions.
Contribution
It offers a formal description and implementation of PRECISE, clarifies its approach, and suggests a roadmap for enhancing the system.
Findings
Initial replication did not fully reproduce PRECISE results
Formalization improved understanding and implementation
System performance shows significant improvement after formalization
Abstract
This report describes an initial replication study of the PRECISE system and develops a clearer, more formal description of the approach. Based on our evaluation, we conclude that the PRECISE results do not fully replicate. However the formalization developed here suggests a road map to further enhance and extend the approach pioneered by PRECISE. After a long, productive discussion with Ana-Maria Popescu (one of the authors of PRECISE) we got more clarity on the PRECISE approach and how the lexicon was authored for the GEO evaluation. Based on this we built a more direct implementation over a repaired formalism. Although our new evaluation is not yet complete, it is clear that the system is performing much better now. We will continue developing our ideas and implementation and generate a future report/publication that more accurately evaluates PRECISE like approaches.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGeographic Information Systems Studies · Semantic Web and Ontologies · Scientific Computing and Data Management
