P
Prashant Shiralkar
Researcher at Amazon.com
Publications - 23
Citations - 1304
Prashant Shiralkar is an academic researcher from Amazon.com. The author has contributed to research in topics: Information extraction & Web page. The author has an hindex of 11, co-authored 20 publications receiving 963 citations. Previous affiliations of Prashant Shiralkar include Indiana University & University of Southern California.
Papers
More filters
Journal ArticleDOI
Computational Fact Checking from Knowledge Networks
Giovanni Luca Ciampaglia,Prashant Shiralkar,Luis M. Rocha,Luis M. Rocha,Johan Bollen,Filippo Menczer,Alessandro Flammini +6 more
TL;DR: It is shown that the complexities of human fact checking can be approximated quite well by finding the shortest path between concept nodes under properly defined semantic proximity metrics on knowledge graphs.
Journal ArticleDOI
The DARPA Twitter Bot Challenge
V. S. Subrahmanian,Amos Azaria,Skylar Durst,Vadim Kagan,Aram Galstyan,Kristina Lerman,Linhong Zhu,Emilio Ferrara,Alessandro Flammini,Filippo Menczer,Andrew Stevens,Alex Dekhtyar,Shuyang Gao,Tad Hogg,Farshad Kooti,Yan Liu,Onur Varol,Prashant Shiralkar,V. G. Vinod Vydiswaran,Qiaozhu Mei,Tim Hwang +20 more
TL;DR: The most recent DARPA Challenge as mentioned in this paper focused on identifying influence bots on a specific topic within Twitter, and three top-ranked teams were identified by the DARPA Social Media in Strategic Communications program.
Proceedings ArticleDOI
Finding Streams in Knowledge Graphs to Support Fact Checking
TL;DR: In this article, an unsupervised network-flow based approach is presented to determine the truthfulness of a statement of fact expressed in the form of a triple. But, the model is expressive in its ability to automatically discover useful patterns and surface relevant facts that may help a human fact checker.
Proceedings ArticleDOI
TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition
TL;DR: The proposed model, Trigger Matching Network, jointly learns trigger representations and soft matching module with self-attention such that can generalize to unseen sentences easily for tagging, and is significantly more cost-effective than the traditional neural NER frameworks.
Journal ArticleDOI
CERES: distantly supervised relation extraction from the semi-structured web
TL;DR: In this article, a method for automatic extraction from semi-structured websites based on distant supervision is presented. But this method is not suitable for settings with complex schemas and information-rich websites.