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 proposes a novelty approach to mitigate the negative transferproblem. In the field of machine learning, the common strategy is to apply theSingle-Task Learning approach in order to train a supervised model to solve aspecific task. Training a robust model requires a lot of data and a significantamount of computational resources, making this solution unfeasible in caseswhere data are unavailable or expensive to gather. Therefore another solution,based on the sharing of information between tasks, has been developed:Multi-Task Learning (MTL). Despite the recent developments regarding MTL, theproblem of negative transfer has still to be solved. Negative transfer is aphenomenon that occurs when noisy information is shared between tasks,resulting in a drop in performance. This paper proposes a new approach tomitigate the negative transfer problem based on the task awareness concept. Theproposed approach results in diminishing the negative transfer together with animprovement of performance over classic MTL solution. Moreover, the proposedapproach has been implemented in two unified architectures to detect Sexism,Hate Speech, and Toxic Language in text comments. The proposed architecturesset a new state-of-the-art both in EXIST-2021 and HatEval-2019 benchmarks.

Mitigating Negative Transfer with Task Awareness for Sexism, Hate Speech, and Toxic Language Detection