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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Chinese BERT models achieve remarkable progress in dealing with grammaticalerrors of word substitution. However, they fail to handle word insertion anddeletion because BERT assumes the existence of a word at each position. Toaddress this, we present a simple and effective Chinese pretrained model. Thebasic idea is to enable the model to determine whether a word exists at aparticular position. We achieve this by introducing a special token\texttt{[null]}, the prediction of which stands for the non-existence of aword. In the training stage, we design pretraining tasks such that the modellearns to predict \texttt{[null]} and real words jointly given the surroundingcontext. In the inference stage, the model readily detects whether a wordshould be inserted or deleted with the standard masked language modelingfunction. We further create an evaluation dataset to foster research on wordinsertion and deletion. It includes human-annotated corrections for 7,726erroneous sentences. Results show that existing Chinese BERT performs poorly ondetecting insertion and deletion errors. Our approach significantly improvesthe F1 scores from 24.1\% to 78.1\% for word insertion and from 26.5\% to68.5\% for word deletion, respectively.

Pretraining Chinese BERT for Detecting Word Insertion and Deletion Errors