ABSTRACT
The DARPA Memex program was established with the goal of funding research into building domain-specific search systems that integrated state-of-the-art focused crawling (domain discovery) information extraction and semantic search, and that could be used by users and domain experts with no programming or technical experience. Domain-specific Insight Graphs (DIG) was proposed and funded under Memex and has led to an end-to-end search system currently being used by over 200 law enforcement for combating human trafficking, by investigators from the Securities and Exchange Commission (SEC) in the US for investigating securities fraud, and for numerous other domains of a difficult, socially consequential (e.g., investigative) and unusual nature.
- Kyle Hundman, Thamme Gowda, Mayank Kejriwal, and Benedikt Boecking. 2017. Always Lurking: Understanding and Mitigating Bias in Online Human Trafficking Detection. arXiv preprint arXiv:1712.00846 (2017).Google Scholar
- Rahul Kapoor, Mayank Kejriwal, and Pedro Szekely. 2017. Using contexts and constraints for improved geotagging of human trafficking webpages Proceedings of the Fourth International ACM Workshop on Managing and Mining Enriched Geo-Spatial Data. ACM, 3. Google ScholarDigital Library
- Mayank Kejriwal, Jiayuan Ding, Runqi Shao, Anoop Kumar, and Pedro Szekely. 2017. FlagIt: A System for Minimally Supervised Human Trafficking Indicator Mining. arXiv preprint arXiv:1712.03086 (2017).Google Scholar
- Mayank Kejriwal and Pedro Szekely. 2017 a. Information extraction in illicit web domains. In Proceedings of the 26th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 997--1006. Google ScholarDigital Library
- Mayank Kejriwal and Pedro Szekely. 2017 b. An Investigative Search Engine for the Human Trafficking Domain International Semantic Web Conference. Springer, 247--262.Google Scholar
- Mayank Kejriwal and Pedro Szekely. 2017 c. Knowledge graphs for social good: An entity-centric search engine for the human trafficking domain. IEEE Transactions on Big Data (2017).Google Scholar
- Mayank Kejriwal and Pedro Szekely. 2017 d. Neural embeddings for populated geonames locations International Semantic Web Conference. Springer, 139--146.Google Scholar
- Mayank Kejriwal, Pedro Szekely, and Craig Knoblock. 2018. Investigative Knowledge Discovery for Combating Illicit Activities. IEEE Intelligent Systems (2018).Google Scholar
- Pedro Szekely, Craig A Knoblock, Jason Slepicka, Andrew Philpot, Amandeep Singh, Chengye Yin, Dipsy Kapoor, Prem Natarajan, Daniel Marcu, Kevin Knight, and others. 2015. Building and using a knowledge graph to combat human trafficking International Semantic Web Conference. Springer, 205--221.Google Scholar
- Linhong Zhu, Majid Ghasemi-Gol, Pedro Szekely, Aram Galstyan, and Craig A Knoblock. 2016. Unsupervised entity resolution on multi-type graphs International Semantic Web Conference. Springer, 649--667.Google Scholar
Index Terms
- Domain-specific Insight Graphs (DIG)
Recommendations
Technology-assisted Investigative Search: A Case Study from an Illicit Domain
CHI EA '18: Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing SystemsFor many, search engines like Google and Bing offer excellent facilities for satisfying information needs. However, a class of needs not currently addressed by generic search engines is investigative search, which has massive potential for using adaptive ...
Understanding Law Enforcement Strategies and Needs for Combating Human Trafficking
CHI '19: Proceedings of the 2019 CHI Conference on Human Factors in Computing SystemsIn working to rescue victims of human trafficking, law enforcement officers face a host of challenges. Working in complex, layered organizational structures, they face challenges of collaboration and communication. Online information is central to every ...
An Investigative Search Engine for the Human Trafficking Domain
The Semantic Web – ISWC 2017AbstractEnabling intelligent search systems that can navigate and facet on entities, classes and relationships, rather than plain text, to answer questions in complex domains is a longstanding aspect of the Semantic Web vision. This paper presents an ...
Comments