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

This paper investigates how to effectively incorporate a pre-trained maskedlanguage model (MLM), such as BERT, into an encoder-decoder (EncDec) model forgrammatical error correction (GEC). The answer to this question is not asstraightforward as one might expect because the previous common methods forincorporating a MLM into an EncDec model have potential drawbacks when appliedto GEC. For example, the distribution of the inputs to a GEC model can beconsiderably different (erroneous, clumsy, etc.) from that of the corpora usedfor pre-training MLMs; however, this issue is not addressed in the previousmethods. Our experiments show that our proposed method, where we firstfine-tune a MLM with a given GEC corpus and then use the output of thefine-tuned MLM as additional features in the GEC model, maximizes the benefitof the MLM. The best-performing model achieves state-of-the-art performances onthe BEA-2019 and CoNLL-2014 benchmarks. Our code is publicly available at:https://github.com/kanekomasahiro/bert-gec.

Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction