SAGEViz: SchemA GEneration and Visualization

Thumbnail Image

Files

2023.emnlp-demo.29.pdf (1.4 MB)

Links to Files

https://aclanthology.org/2023.emnlp-demo.29/

Permanent Link

http://hdl.handle.net/11603/31099

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection
UMBC Student Collection

Author/Creator

Author/Creator ORCID

Date

2023-12

Type of Work

conference papers and proceedings
Text

Department

Program

Citation of Original Publication

Devare, Sugam, Mahnaz Koupaee, Gautham Gunapati, Sayontan Ghosh, Sai Vallurupalli, Yash Kumar Lal, Francis Ferraro, et al. “SAGEViz: SchemA GEneration and Visualization.” In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, edited by Yansong Feng and Els Lefever, 328–35. Singapore: Association for Computational Linguistics, 2023. https://aclanthology.org/2023.emnlp-demo.29.

Rights

This work was written as part of one of the author's official duties as an Employee of the United States Government and is therefore a work of the United States Government. In accordance with 17 U.S.C. 105, no copyright protection is available for such works under U.S. Law.
Public Domain

Subjects

Abstract

Schema induction involves creating a graph representation depicting how events unfold in a scenario. We present SAGEViz, an intuitive and modular tool that utilizes human-AI collaboration to create and update complex schema graphs efficiently, where multiple annotators (humans and models) can work simultaneously on a schema graph from any domain. The tool consists of two components: (1) a curation component powered by plug-and-play event language models to create and expand event sequences while human annotators validate and enrich the sequences to build complex hierarchical schemas, and (2) an easy-to-use visualization component to visualize schemas at varying levels of hierarchy. Using supervised and few-shot approaches, our event language models can continually predict relevant events starting from a seed event. We conduct a user study and show that users need less effort in terms of interaction steps with SAGEViz to generate schemas of better quality. We also include a video demonstrating the system.