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

While performance of many text classification tasks has been recentlyimproved due to Pre-trained Language Models (PLMs), in this paper we show thatthey still suffer from a performance gap when the underlying distribution oftopics changes. For example, a genre classifier trained on \textit{political}topics often fails when tested on documents about \textit{sport} or\textit{medicine}. In this work, we quantify this phenomenon empirically with alarge corpus and a large set of topics. Consequently, we verify that domaintransfer remains challenging both for classic PLMs, such as BERT, and formodern large models, such as GPT-3. We also suggest and successfully test apossible remedy: after augmenting the training dataset withtopically-controlled synthetic texts, the F1 score improves by up to 50\% forsome topics, nearing on-topic training results, while others show little to noimprovement. While our empirical results focus on genre classification, ourmethodology is applicable to other classification tasks such as gender,authorship, or sentiment classification. The code and data to replicate theexperiments are available at https://github.com/dminus1/genre

BERT Goes Off-Topic: Investigating the Domain Transfer Challenge using Genre Classification