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.
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