Improving Multilingual Named Entity Recognition with Wikipedia Entity Type Mapping
Authors | Jian Ni Radu Florian |
|---|---|
Publication date | 2016 |
DOI | 10.18653/v1/D16-1135 |
Links | Original Preprint |
Improving Multilingual Named Entity Recognition with Wikipedia Entity Type Mapping - scientific work related to Wikipedia quality published in 2016, written by Jian Ni and Radu Florian.
Overview
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, authors utilize Wikipedia as an open knowledge base to improve multilingual NER systems. Central to 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, authors develop several approaches to improve an NER system. Authors 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).
Embed
Wikipedia Quality
Ni, Jian; Florian, Radu. (2016). "[[Improving Multilingual Named Entity Recognition with Wikipedia Entity Type Mapping]]".DOI: 10.18653/v1/D16-1135.
English Wikipedia
{{cite journal |last1=Ni |first1=Jian |last2=Florian |first2=Radu |title=Improving Multilingual Named Entity Recognition with Wikipedia Entity Type Mapping |date=2016 |doi=10.18653/v1/D16-1135 |url=https://wikipediaquality.com/wiki/Improving_Multilingual_Named_Entity_Recognition_with_Wikipedia_Entity_Type_Mapping}}
HTML
Ni, Jian; Florian, Radu. (2016). "<a href="https://wikipediaquality.com/wiki/Improving_Multilingual_Named_Entity_Recognition_with_Wikipedia_Entity_Type_Mapping">Improving Multilingual Named Entity Recognition with Wikipedia Entity Type Mapping</a>".DOI: 10.18653/v1/D16-1135.
