Enhanced Named Entity Recognition with Semantic Dependency

Dependency-based models for the named entity recognition (NER) task have shown promising results by capturing long-distance relationships between words in a sentence. However, while existing focus on syntactic dependency entities, we are unaware of any work that considers semantic dependency. In this work, study usefulness information NER. We propose NER model is guided graphs instead trees. The extensive experiments illustrate effectiveness proposed and advantages over Also, it shows correlations performance annotations qualities.