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

Lexical Substitution discovers appropriate substitutes for a given targetword in a context sentence. However, the task fails to consider substitutesthat are of equal or higher proficiency than the target, an aspect that couldbe beneficial for language learners looking to improve their writing. To bridgethis gap, we propose a new task, language proficiency-oriented lexicalsubstitution. We also introduce ProLex, a novel benchmark designed to assesssystems' ability to generate not only appropriate substitutes but alsosubstitutes that demonstrate better language proficiency. Besides thebenchmark, we propose models that can automatically perform the new task. Weshow that our best model, a Llama2-13B model fine-tuned with task-specificsynthetic data, outperforms ChatGPT by an average of 3.2% in F-score andachieves comparable results with GPT-4 on ProLex.

ProLex: A Benchmark for Language Proficiency-oriented Lexical Substitution