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

Genre identification is a subclass of non-topical text classification. Themain difference between this task and topical classification is that genres,unlike topics, usually do not correspond to simple keywords, and thus they needto be defined in terms of their functions in communication. Neural models basedon pre-trained transformers, such as BERT or XLM-RoBERTa, demonstrate SOTAresults in many NLP tasks, including non-topical classification. However, inmany cases, their downstream application to very large corpora, such as thoseextracted from social media, can lead to unreliable results because of datasetshifts, when some raw texts do not match the profile of the training set. Tomitigate this problem, we experiment with individual models as well as withtheir ensembles. To evaluate the robustness of all models we use a predictionconfidence metric, which estimates the reliability of a prediction in theabsence of a gold standard label. We can evaluate robustness via the confidencegap between the correctly classified texts and the misclassified ones on alabeled test corpus, higher gaps make it easier to improve our confidence thatour classifier made the right decision. Our results show that for all of theclassifiers tested in this study, there is a confidence gap, but for theensembles, the gap is bigger, meaning that ensembles are more robust than theirindividual models.

Estimating Confidence of Predictions of Individual Classifiers and Their Ensembles for the Genre Classification Task