English

Morphological Embeddings for Named Entity Recognition in Morphologically Rich Languages

Computation and Language 2017-06-05 v1

Abstract

In this work, we present new state-of-the-art results of 93.59,% and 79.59,% for Turkish and Czech named entity recognition based on the model of (Lample et al., 2016). We contribute by proposing several schemes for representing the morphological analysis of a word in the context of named entity recognition. We show that a concatenation of this representation with the word and character embeddings improves the performance. The effect of these representation schemes on the tagging performance is also investigated.

Keywords

Cite

@article{arxiv.1706.00506,
  title  = {Morphological Embeddings for Named Entity Recognition in Morphologically Rich Languages},
  author = {Onur Gungor and Eray Yildiz and Suzan Uskudarli and Tunga Gungor},
  journal= {arXiv preprint arXiv:1706.00506},
  year   = {2017}
}

Comments

Working draft

R2 v1 2026-06-22T20:07:00.177Z