Graph Convolutional Networks for Named Entity Recognition

Abstract

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.

Accepted at the 16th International Workshop on Treebanks and Linguistic Theories

References in corpus (3)

• Natural Language Processing (almost) from Scratch
• Attending to Characters in Neural Sequence Labeling Models
• Linguistic Knowledge as Memory for Recurrent Neural Networks

Cited by in corpus (5)

• Structural Neural Encoders for AMR-to-text Generation
• GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling
• Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information
• InsertGNN: Can Graph Neural Networks Outperform Humans in TOEFL Sentence Insertion Problem?
• Graph Convolutional Network for Swahili News Classification