A framework for named entity recognition in the open domain

In this paper, a system for Named Entity Recognition in the Open domain (NERO) is described. It is concerned with recognition of various types of entity, types that will be appropriate for Information Extraction in any scenario context. The recognition task is performed by identifying normally capitalised phrases in a document and then submitting queries to a search engine to find potential hypernyms of the capitalised sequences. These hypernyms are then clustered to derive a typology of named entities for the document. The hypernyms of the normally capitalised phrases are used to classify them with respect to this typology. The method is tested on a small corpus and its classifications are evaluated. Finally, conclusions are drawn and future work considered.

• Type: Conference
• Year: 2003
• Where: RANLP
• Authors: Richard J. Evans
• Keywords: Named Entity Recognition, Natural Language Processing, Potential Hypernyms, RANLP 2003, Recognition Task