Abstract | ||
---|---|---|
We describe a simple approach to named-entity recognition (NER), aimed initially at the Dutch language, but potentially applicable to other languages. Our NER system employs a two-stage architecture, with handcrafted but dataset-independent features for both stages, and is on a par with state-of-the-art systems described in the literature. Notably, our approach does not depend on language-specific assets such as gazetteers. The resulting system is quite fast and is implemented in less than 500 lines of code. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-31178-9_17 | NLDB |
Keywords | Field | DocType |
state-of-the-art system,resulting system,language-specific asset,ner system,dutch language,simple approach,two-stage named-entity recognition,two-stage architecture,dataset-independent feature | Architecture,Computer science,Natural language processing,Artificial intelligence,Perceptron,Named-entity recognition,Source lines of code | Conference |
Citations | PageRank | References |
5 | 0.48 | 7 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lars Buitinck | 1 | 110 | 6.31 |
Maarten Marx | 2 | 1372 | 97.86 |