English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

To better tackle the named entity recognition (NER) problem on languages withlittle/no labeled data, cross-lingual NER must effectively leverage knowledgelearned from source languages with rich labeled data. Previous works oncross-lingual NER are mostly based on label projection with pairwise texts ordirect model transfer. However, such methods either are not applicable if thelabeled data in the source languages is unavailable, or do not leverageinformation contained in unlabeled data in the target language. In this paper,we propose a teacher-student learning method to address such limitations, whereNER models in the source languages are used as teachers to train a studentmodel on unlabeled data in the target language. The proposed method works forboth single-source and multi-source cross-lingual NER. For the latter, wefurther propose a similarity measuring method to better weight the supervisionfrom different teacher models. Extensive experiments for 3 target languages onbenchmark datasets well demonstrate that our method outperforms existingstate-of-the-art methods for both single-source and multi-source cross-lingualNER.

Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language