Self-Adaptive Named Entity Recognition by Retrieving Unstructured Knowledge

TL;DR

This paper introduces a self-adaptive NER approach that retrieves unstructured external knowledge to improve recognition accuracy for uncertain entities, reducing the need for extensive training data.

Contribution

It proposes a novel two-stage retrieval model that enhances NER by leveraging unstructured knowledge for uncertain entities, outperforming existing baselines.

Findings

Outperforms strong baselines by 2.35 F1 points on CrossNER datasets.

Effectively uses uncertain entities as queries for knowledge retrieval.

Improves NER accuracy without extensive domain-specific training data.

Abstract

Although named entity recognition (NER) helps us to extract domain-specific entities from text (e.g., artists in the music domain), it is costly to create a large amount of training data or a structured knowledge base to perform accurate NER in the target domain. Here, we propose self-adaptive NER, which retrieves external knowledge from unstructured text to learn the usages of entities that have not been learned well. To retrieve useful knowledge for NER, we design an effective two-stage model that retrieves unstructured knowledge using uncertain entities as queries. Our model predicts the entities in the input and then finds those of which the prediction is not confident. Then, it retrieves knowledge by using these uncertain entities as queries and concatenates the retrieved text to the original input to revise the prediction. Experiments on CrossNER datasets demonstrated that our model outperforms strong baselines by 2.35 points in F1 metric.