Graph Convolutional Networks for Named Entity Recognition
This work addresses named entity recognition for natural language processing applications, presenting an incremental improvement by leveraging dependency grammar.
The paper tackled the problem of named entity recognition by investigating the role of dependency trees using graph convolutional networks, resulting in consistent performance improvements on the OntoNotes dataset without heavy feature engineering or language-specific knowledge.
In this paper we investigate the role of the dependency tree in a named entity recognizer upon using a set of GCN. We perform a comparison among different NER architectures and show that the grammar of a sentence positively influences the results. Experiments on the ontonotes dataset demonstrate consistent performance improvements, without requiring heavy feature engineering nor additional language-specific knowledge.