jjfiv / ecir2015timebooks

Code for "Retrieving Time from Scanned Books" which appeared at ECIR 2015

This repository contains code for the paper "Retrieving Time from Scanned Books". If you use this paper or the dataset, please cite:

Foley, J. and Allan, J., "Retrieving Time from Scanned Books," Proceedings of the 37th European Conference on Information Retrieval (ECIR 2015), Vienna, Austria, March 29 - April 2, 2015, pp. 221-232.

Build the code:

mvn package 

• try -DskipTests if they fail for you; they use temporary files which can be wonky
• Maven should automatically pull in all dependencies you need

Building disclaimer

This repository contains code which built as of April 1st, 2015 on Ubuntu Linux with Oracle Java 8 and Maven v. 3.0.5. May the odds be ever in your favor if you're coming to this much later. Perhaps it can be a good reference anyway.

ecir2015timebooks's Issues

Publish list of book IDs please

Could you please publish the list of the 50,228 Internet Archive book IDs for the books which were used in the evaluation? That would be useful to people who want to either reproduce your results or experiment on the same corpus.