Morphological Embeddings for Named Entity Recognition in Morphologically Rich Languages
This work addresses improved accuracy for named entity recognition in languages with complex morphology, but it is incremental as it builds on an existing model.
The paper tackled named entity recognition in morphologically rich languages like Turkish and Czech by proposing morphological embedding schemes, achieving state-of-the-art results of 93.59% and 79.59% respectively.
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.