Events Calendar

RECRUITING SEMINAR

Speaker: Mayank Kejriwal, University of Texas at Austin

Talk Title: Populating a Linked Data Entity Name System

Series: Recruitng Seminar

Abstract: Resource Description Framework (RDF) is a graph-based data model used to publish data as a Web of Linked Data. RDF is an emergent foundation for large-scale data integration. An Entity Name System (ENS) is a thesaurus for entities, and is a crucial component in a data integration architecture. Populating a Linked Data ENS is equivalent to solving an Artificial Intelligence problem called instance matching, which concerns identifying pairs of entities referring to the same underlying entity.

This talk describes a system that automatically populates an ENS in a domain-independent fashion. Automation is addressed through inexpensive but well-performing heuristics that are used to generate a training set, which is employed by other machine learning algorithms in the pipeline. Data-driven alignment algorithms are adapted to deal with structural heterogeneity in RDF graphs. The full system is scaled by implementing it on cloud infrastructure using MapReduce algorithms.



Biography: Mayank Kejriwal is finishing up his Ph.D in Computer Science at the University of Texas at Austin under the supervision of Daniel P. Miranker. His research focuses on instance-level information integration in the Semantic Web, and has been published in the International Conference on Data Mining, the Journal of Web Semantics, the International Semantic Web Conference, and the Extended Semantic Web Conference, where he won a best paper award at the 4th annual Know@LOD workshop. Prior to joining UT Austin in 2012, he obtained a dual undergraduate degree in Computer Engineering and Engineering Physics from the University of Illinois at Urbana-Champaign.


Host: Craig Knoblock

Webcast: Webcast:http://webcasterms1.isi.edu/mediasite/Viewer/?peid=cd1440ac1ea54794b12eab29e42d60ee1d

Location: Information Science Institute (ISI) - 11th floor Large CR

WebCast Link: Webcast:http://webcasterms1.isi.edu/mediasite/Viewer/?peid=cd1440ac1ea54794b12eab29e42d60ee1d

Audiences: Everyone Is Invited

Contact: Alma Nava / Information Sciences Institute