%0 Conference Proceedings %T A Study of the Importance of External Knowledge in the Named Entity Recognition Task %A Seyler, Dominic %A Dembelova, Tatiana %A Del Corro, Luciano %A Hoffart, Johannes %A Weikum, Gerhard %Y Gurevych, Iryna %Y Miyao, Yusuke %S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) %D 2018 %8 July %I Association for Computational Linguistics %C Melbourne, Australia %F seyler-etal-2018-study %X In this work, we discuss the importance of external knowledge for performing Named Entity Recognition (NER). We present a novel modular framework that divides the knowledge into four categories according to the depth of knowledge they convey. Each category consists of a set of features automatically generated from different information sources, such as a knowledge-base, a list of names, or document-specific semantic annotations. Further, we show the effects on performance when incrementally adding deeper knowledge and discuss effectiveness/efficiency trade-offs. %R 10.18653/v1/P18-2039 %U https://aclanthology.org/P18-2039 %U https://doi.org/10.18653/v1/P18-2039 %P 241-246