Neural Named Entity Recognition for Kazakh
This addresses the problem of data sparsity in named entity recognition for under-resourced morphologically complex languages, offering a method that could be applied to similar languages.
The authors tackled named entity recognition for morphologically complex languages like Kazakh, which suffers from data sparsity due to extensive word variations, by introducing root and entity tag embeddings with a tensor layer to neural networks, achieving state-of-the-art performance that outperforms character-based approaches.
We present several neural networks to address the task of named entity recognition for morphologically complex languages (MCL). Kazakh is a morphologically complex language in which each root/stem can produce hundreds or thousands of variant word forms. This nature of the language could lead to a serious data sparsity problem, which may prevent the deep learning models from being well trained for under-resourced MCLs. In order to model the MCLs' words effectively, we introduce root and entity tag embedding plus tensor layer to the neural networks. The effects of those are significant for improving NER model performance of MCLs. The proposed models outperform state-of-the-art including character-based approaches, and can be potentially applied to other morphologically complex languages.