We are proud to announce the public service of our STICS search engine:
developed at the Max Planck Institute for Informatics, presented at the SIGIR 2014 as a
By extending the Google slogan of "things, not strings" to support also entity
categories, STICS provides powerful functionality for querying and analyzing news and
other text corpora in terms of entities, semantic classes, and text phrases. STICS is
based on state-of-the-art methods for named entity recognition and disambiguation (AIDA
), linking them to knowledge bases like YAGO and the Wikipedia category system. The
online service currently has indexed 1,000,000 news articles since June 2013, with more
than 22 million entity occurrences of 300,000 distinct entities.
You can search, for example, for presidents of the United States and the JFK airport, and
see how STICS distinguishes between JFK and JFK:
We are looking forward to your feedback!
The STICS team
at the Max Planck Institute for Informatics
 J. Hoffart, M. A. Yosef, I. Bordino, H. Fürstenau, M. Pinkal, M. Spaniol, B. Taneva,
S. Thater, G. Weikum. Robust Disambiguation of Named Entities in Text. EMNLP 2011 (
- source available under the CC-BY-SA-NC license
 J. Hoffart, D. Milchevski, G. Weikum. STICS: Searching with Strings, Things, and Cats.
Demo at SIGIR 2014. ( http://www.mpi-inf.mpg.de/yago-naga/stics