Skip to main content
U.S. flag

An official website of the United States government

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

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.

Overview of the TREC 2019 Deep Learning Track

Published

Author(s)

Ellen M. Voorhees, Nick Craswell, Bhaskar Mitra, Daniel Campos, Emine Yilmaz

Abstract

The Deep Learning Track is a new track for TREC 2019, with the goal of studying ad hoc ranking in a large data regime. It is the first track with large human-labeled training sets, introducing two sets corresponding to two tasks, each with rigorous TREC-style blind evaluation and reusable test sets. The document retrieval task has a corpus of 3.2 million documents with 367 thousand training queries, for which we generate a reusable test set of 43 queries. The passage retrieval task has a corpus of 8.8 million passages with 503 thousand training queries, for which we generate a reusable test set of 43 queries. This year 15 groups submitted a total of 75 runs, using various combinations of deep learning, transfer learning and traditional IR ranking methods. Deep learning runs significantly outperformed traditional IR runs. Possible explanations for this result are that we introduced large training data and we included deep models trained on such data in our judging pools, whereas some past studies did not have such training data or pooling.
Citation
OTHER - SP1250
Report Number
SP1250

Keywords

deep learning, information retrieval, test collections, TREC

Citation

Voorhees, E. , Craswell, N. , Mitra, B. , Campos, D. and Yilmaz, E. (2020), Overview of the TREC 2019 Deep Learning Track, OTHER, National Institute of Standards and Technology, Gaithersburg, MD (Accessed March 4, 2024)
Created July 27, 2020, Updated February 14, 2023