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

WSD (Word Sense Disambiguation) is the task of identifying which sense of aword is meant in a sentence or other segment of text. Researchers have workedon this task (e.g. Pustejovsky, 2002) for years but it's still a challengingone even for SOTA (state-of-the-art) LMs (language models). The new dataset,TempoWiC introduced by Loureiro et al. (2022b) focuses on the fact that wordschange over time. Their best baseline achieves 70.33% macro-F1. In this work,we use two different losses simultaneously to train RoBERTa-basedclassification models. We also improve our model by using another similardataset to generalize better. Our best configuration beats their best baselineby 4.23% and reaches 74.56% macroF1.

Using Two Losses and Two Datasets Simultaneously to Improve TempoWiC Accuracy