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

Pre-trained Language Models (PLMs) have achieved remarkable performance gainsacross numerous downstream tasks in natural language understanding. VariousChinese PLMs have been successively proposed for learning better Chineselanguage representation. However, most current models use Chinese characters asinputs and are not able to encode semantic information contained in Chinesewords. While recent pre-trained models incorporate both words and characterssimultaneously, they usually suffer from deficient semantic interactions andfail to capture the semantic relation between words and characters. To addressthe above issues, we propose a simple yet effective PLM CLOWER, which adoptsthe Contrastive Learning Over Word and charactER representations. Inparticular, CLOWER implicitly encodes the coarse-grained information (i.e.,words) into the fine-grained representations (i.e., characters) throughcontrastive learning on multi-grained information. CLOWER is of great value inrealistic scenarios since it can be easily incorporated into any existingfine-grained based PLMs without modifying the production pipelines.Extensiveexperiments conducted on a range of downstream tasks demonstrate the superiorperformance of CLOWER over several state-of-the-art baselines.

CLOWER: A Pre-trained Language Model with Contrastive Learning over Word and Character Representations