RULE-BASED NAMED ENTITY RECOGNITION FOR GREEK FINANCIAL TEXTS
Dimitra Farmakiotou, Vangelis Karkaletsis, John Koutsias, George Sigletos, Constantine D. Spyropoulos, Panagiotis Stamatopoulos · 2000
The identification and classification of proper names (named entity recognition) is considered an important task in the area of Information Retrieval and Extraction. A typical named entity recognition (NER) system mainly consists of a lexicon and a grammar. When moving to a new domain, these lexical resources should be customised, either manually or exploiting machine learning techniques. In this paper, we present a NER system based on hand crafted lexical resources. The system is part of a Greek information extraction system and was tested on a Greek corpus of financial news with satisfactory results. Keywords: information extraction, named entity recognition, pattern matching 1. INTRODUCTION Information Extraction (IE) is the task of automatically extracting information of interest from unconstrained text creating a structured representation of this information. An IE task involves two main sub-tasks: the recognition of the named entities involved in an event and the recognition o...