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

The increasing privacy concerns on personal private text data promote thedevelopment of federated learning (FL) in recent years. However, the existingstudies on applying FL in NLP are not suitable to coordinate participants withheterogeneous or private learning objectives. In this study, we further broadenthe application scope of FL in NLP by proposing an Assign-Then-Contrast(denoted as ATC) framework, which enables clients with heterogeneous NLP tasksto construct an FL course and learn useful knowledge from each other.Specifically, the clients are suggested to first perform local training withthe unified tasks assigned by the server rather than using their own learningobjectives, which is called the Assign training stage. After that, in theContrast training stage, clients train with different local learning objectivesand exchange knowledge with other clients who contribute consistent and usefulmodel updates. We conduct extensive experiments on six widely-used datasetscovering both Natural Language Understanding (NLU) and Natural LanguageGeneration (NLG) tasks, and the proposed ATC framework achieves significantimprovements compared with various baseline methods. The source code isavailable at\url{https://github.com/alibaba/FederatedScope/tree/master/federatedscope/nlp/hetero_tasks}.

Collaborating Heterogeneous Natural Language Processing Tasks via Federated Learning