Improving Multilingual Named Entity Recognition with Wikipedia Entity Type Mapping

TL;DR

This paper leverages Wikipedia to create multilingual entity type mappings, enhancing NER systems' accuracy, especially for unseen entities and low-resource languages, with up to 18.3 F1 score improvements.

Contribution

It introduces a novel method to construct high-coverage multilingual Wikipedia entity type mappings from weakly annotated data, improving NER performance without additional human annotation.

Findings

Improved NER accuracy on 6 languages.

Up to 18.3 F1 score increase for unseen entities.

Effective in low-resource and new domain scenarios.

Abstract

The state-of-the-art named entity recognition (NER) systems are statistical machine learning models that have strong generalization capability (i.e., can recognize unseen entities that do not appear in training data) based on lexical and contextual information. However, such a model could still make mistakes if its features favor a wrong entity type. In this paper, we utilize Wikipedia as an open knowledge base to improve multilingual NER systems. Central to our approach is the construction of high-accuracy, high-coverage multilingual Wikipedia entity type mappings. These mappings are built from weakly annotated data and can be extended to new languages with no human annotation or language-dependent knowledge involved. Based on these mappings, we develop several approaches to improve an NER system. We evaluate the performance of the approaches via experiments on NER systems trained for 6 languages. Experimental results show that the proposed approaches are effective in improving the accuracy of such systems on unseen entities, especially when a system is applied to a new domain or it is trained with little training data (up to 18.3 F1 score improvement).