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

Recently, Chinese Spell Checking(CSC), a task to detect erroneous charactersin a sentence and correct them, has attracted extensive interest because of itswide applications in various NLP tasks. Most of the existing methods haveutilized BERT to extract semantic information for CSC task. However, thesemethods directly take sentences with only a few errors as inputs, where thecorrect characters may leak answers to the model and dampen its ability tocapture distant context; while the erroneous characters may disturb thesemantic encoding process and result in poor representations. Based on suchobservations, this paper proposes an n-gram masking layer that masks currentand/or surrounding tokens to avoid label leakage and error disturbance.Moreover, considering that the mask strategy may ignore multi-modal informationindicated by errors, a novel dot-product gating mechanism is proposed tointegrate the phonological and morphological information with semanticrepresentation. Extensive experiments on SIGHAN datasets have demonstrated thatthe pluggable n-gram masking mechanism can improve the performance of prevalentCSC models and the proposed methods in this paper outperform multiple powerfulstate-of-the-art models.

Block the Label and Noise: An N-Gram Masked Speller for Chinese Spell Checking