Abstract
Much past work has focused on extracting information like events, entities, and relations from documents. Very little work has focused on analyzing these results for better model understanding. In this paper, we introduce a curation interface that takes an Information Extraction (IE) system’s output in a pre-defined format and generates a graphical representation of its elements. The interface supports editing while curating schemas for complex events like Improvised Explosive Device (IED) based scenarios. We identify various schemas that either have linear event chains or contain parallel events with complicated temporal ordering. We iteratively update an induced schema to uniquely identify events specific to it, add optional events around them, and prune unnecessary events. The resulting schemas are improved and enriched versions of the machine-induced versions.
Cite
CITATION STYLE
Mishra, P., Malhotra, A., Brown, S. W., Palmer, M., & Kazeminejad, G. (2021). A graphical interface for curating schemas. In ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations (pp. 159–166). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.acl-demo.19
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.