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.
@article{arxiv.1709.10053,
title = {Graph Convolutional Networks for Named Entity Recognition},
author = {A. Cetoli and S. Bragaglia and A. D. O'Harney and M. Sloan},
journal= {arXiv preprint arXiv:1709.10053},
year = {2018}
}
Comments
Accepted at the 16th International Workshop on Treebanks and Linguistic Theories