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

Incorporating lattices into character-level Chinese named entity recognitionis an effective method to exploit explicit word information. Recent worksextend recurrent and convolutional neural networks to model lattice inputs.However, due to the DAG structure or the variable-sized potential word set forlattice inputs, these models prevent the convenient use of batched computation,resulting in serious inefficient. In this paper, we propose a porouslattice-based transformer encoder for Chinese named entity recognition, whichis capable to better exploit the GPU parallelism and batch the computationowing to the mask mechanism in transformer. We first investigate thelattice-aware self-attention coupled with relative position representations toexplore effective word information in the lattice structure. Besides, tostrengthen the local dependencies among neighboring tokens, we propose a novelporous structure during self-attentional computation processing, in which everytwo non-neighboring tokens are connected through a shared pivot node.Experimental results on four datasets show that our model performs up to 9.47times faster than state-of-the-art models, while is roughly on a par with itsperformance. The source code of this paper can be obtained fromhttps://github.com/xxx/xxx.

Porous Lattice-based Transformer Encoder for Chinese NER