Files and links (1)
Open Access CC BY V4.0
Conference proceeding
STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System
Companion Proceedings of the ACM Web Conference 2026, pp.69-72
ACM Conferences
WWW '26: The ACM Web Conference 2026 (Dubai, United Arab Emirates, 29/06/2026–03/07/2026)
2026
Abstract
Extracting structured knowledge from unstructured data still faces practical limitations: entity and event extraction pipelines remain brittle, knowledge graph construction requires costly ontology engineering, and cross-domain generalization is rarely production-ready. In contrast, space and time provide universal contextual anchors that naturally align heterogeneous information and benefit downstream tasks such as retrieval and reasoning. We introduce STIndex, an end-to-end system that structures unstructured content into a multidimensional spatiotemporal data warehouse. Users define domain-specific analysis dimensions with configurable hierarchies, while large language models perform context-aware extraction and grounding. STIndex integrates document-level memory, geocoding correction, and quality validation, and offers an interactive analytics dashboard for visualization, clustering, burst detection, and entity network analysis. In evaluation on a public health benchmark, STIndex improves spatiotemporal entity extraction F1 by 4.37% (GPT-4o-mini) and 3.60% (Qwen3-8B). A live demonstration and open-source code are available at https://stindex.ai4wa.com/dashboard.
Details
- Title
- STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System
- Authors/Creators
- Wenxiao Zhang - The University of Western AustraliaYu Liu - Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, ChinaQiang Sun - The University of Western AustraliaYihao Ding - The University of Western AustraliaSirui Li - Murdoch UniversityYanbing Liu - Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, ChinaJin B. Hong - The University of Western AustraliaWei Liu - The University of Western Australia
- Publication Details
- Companion Proceedings of the ACM Web Conference 2026, pp.69-72
- Conference
- WWW '26: The ACM Web Conference 2026 (Dubai, United Arab Emirates, 29/06/2026–03/07/2026)
- Series
- ACM Conferences
- Publisher
- ACM Digital Library
- Number of pages
- 4
- Identifiers
- 991005886493307891
- Copyright
- ©2026 Copyright held by the owner/author(s).
- Murdoch Affiliation
- School of Information Technology
- Language
- English
- Resource Type
- Conference proceeding
Metrics
1 File views/ downloads
2 Record Views