Exploiting Morpheme and Cross-lingual Knowledge to Enhance Mongolian Named Entity Recognition

Mongolian named entity recognition (NER) is not only one of the most crucial and fundamental tasks in natural language processing, but also an important step to improve performance downstream such as information retrieval, machine translation, dialog system. However, traditional NER models heavily rely on feature engineering. Even worse, complex morphological structure words makes data sparser. To alleviate engineering sparsity recognition, we propose a novel framework with Multi-Knowledge Enhancement (MKE-NER) . Specifically, introduce both linguistic knowledge through morpheme representation cross-lingual from Mongolian-Chinese parallel corpus. Furthermore, design two methods exploit sufficiently, i.e., annotation projection. Experimental results demonstrate effectiveness our MKE-NER model, which outperforms strong baselines achieves best (94.04% F1 score) benchmark. Particularly, extensive experiments different scales highlight superiority method low-resource scenarios.