Skip to main content
U.S. flag

An official website of the United States government

Dot gov

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Https

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Ian Soboroff

Group Leader

Dr. Ian Soboroff is a computer scientist and leader of the Retrieval Group at the National Institute of Standards and Technology (NIST). The Retrieval Group organizes the Text REtrieval Conference (TREC), the Text Analysis Conference (TAC), and the TREC Video Retrieval Evaluation (TRECVID). These are all large, community-based research workshops that drive the state-of-the-art in information retrieval, video search, web search, information extraction, text summarization and other areas of information access. He has co-authored many publications in information retrieval evaluation, test collection building, text filtering, collaborative filtering, and intelligent software agents. His current research interests include building test collections for social media environments and nontraditional retrieval tasks.

Publications

PSCR 2020_Social Media Incident Streams

Author(s)
Ian M. Soboroff
The ubiquity of mobile internet-enabled devices combined with wide-spread social media use during emergencies is posing new challenges for response personnel

International Workshop on Deep Video Understanding

Author(s)
Keith Curtis, George M. Awad, Shahzad K. Rajput, Ian M. Soboroff
This is the introduction paper to the International Workshop on Deep Video Understanding. In recent years, a growing trend towards working on understanding

Overview of the NIST 2016 LoReHLT Evaluation

Author(s)
Audrey N. Tong, Lukasz L. Diduch, Jonathan G. Fiscus, Yasaman Haghpanah, Shudong Huang, David M. Joy, Kay Peterson, Ian M. Soboroff
Initiated in conjunction with DARPA's Low Resource Languages for Emergent Incidents (LORELEI) Program, the NIST LoReHLT (Low Re-source Human Language Technology

Using Replicates in Information Retrieval Evaluation

Author(s)
Ellen M. Voorhees, Daniel V. Samarov, Ian M. Soboroff
This paper explores a method for more accurately estimating the main effect of the system in a typical test-collection-based evaluation of information retrieval
Created October 9, 2019