KARL-Trans-NER: Knowledge Aware Representation Learning for Named Entity Recognition using Transformers

TL;DR

This paper introduces KARL-Trans-NER, a knowledge-aware transformer-based model that enhances named entity recognition by integrating large-scale knowledge bases, leading to improved accuracy and generalization on multiple datasets.

Contribution

The paper proposes a novel Knowledge Aware Representation Learning (KARL) network that incorporates world knowledge into transformer models for NER, addressing existing challenges and boosting performance.

Findings

Significantly improved NER results on CoNLL 2003, CoNLL++, and OntoNotes v5 datasets.

Enhanced generalization to unseen entities in real-world scenarios.

Effective integration of knowledge bases as fact triplets for feature augmentation.

Abstract

The inception of modeling contextual information using models such as BERT, ELMo, and Flair has significantly improved representation learning for words. It has also given SOTA results in almost every NLP task - Machine Translation, Text Summarization and Named Entity Recognition, to name a few. In this work, in addition to using these dominant context-aware representations, we propose a Knowledge Aware Representation Learning (KARL) Network for Named Entity Recognition (NER). We discuss the challenges of using existing methods in incorporating world knowledge for NER and show how our proposed methods could be leveraged to overcome those challenges. KARL is based on a Transformer Encoder that utilizes large knowledge bases represented as fact triplets, converts them to a graph context, and extracts essential entity information residing inside to generate contextualized triplet representation for feature augmentation. Experimental results show that the augmentation done using KARL can considerably boost the performance of our NER system and achieve significantly better results than existing approaches in the literature on three publicly available NER datasets, namely CoNLL 2003, CoNLL++, and OntoNotes v5. We also observe better generalization and application to a real-world setting from KARL on unseen entities.