Extended Named Entity Hierarchy

By Satoshi Sekine, Kiyoshi Sudo, Chikashi Nobata. International Conference on Language Resources and Evaluation, 2002

307 citations recorded by the source corpus.

The tagging of Named Entities (NE), the names of particular things or classes and numeric expressions, is regarded as an important component technology for many NLP applications. These applications include Information Extraction, from which it was born, QuestionAnswering, Summarization and Information Retrieval. However, up to now, the number of NE types has been quite limited, 7 in MUC, 8 in IREX and 5 in the ACE program. Many more kinds of things have proper names or proper classes of expressions, and also finer distinctions are needed for some applications. We now propose a Named Entity hierarchy which contains about 150 NE types. The focus of this paper is the design of the hierarchy and we would like to provide this resource for any application. We report the design and development procedure of the hierarchy.

Subfields: Artificial Intelligence, Computer Networks and Communications, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/f664c4a6aee50411f1db79999fd5e7c88a35b926

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

Jochen L. Leidner

In Management Science and Operations Research

Citations in the corpus

Exploiting Wikipedia as External Knowledge for Named Entity Recognition (2007, background): “…Fabio Capello last season , with O O O O B-PER O O O O O B-coaches I-coaches However, the merit of using such speciﬁc Wikipedia labels will be much greater when we aim at developing NER systems for more ﬁne-grained NE categories such as proposed in Sekine et al. (2002) or Shinzato et al. (2006).”
Learning multilingual named entity recognition from Wikipedia (2013, unknown): “However, Sekine’s [68] scheme would have been equally suitable.”
Discovering Relations among Named Entities from Large Corpora (2004, background): “For example, Sekine proposed 150 types of named entities (Sekine et al., 2002).”
KIM - Semantic Annotation Platform (2003, background): “NE type hierarchies design has been discussed in [38].”
Toponym resolution in text: annotation, evaluation and applications of spatial grounding (2007, methodology): “• how to ground unconstrained text in space and time; currently, most research is on temporal processing, especially in the TERQAS project within the US DARPA ‘AQUAINT’ programme (see Setzer (2001); Pustejovsky and Mani (2003) for the development of a recent temporal markup scheme, on which subseque”