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

In multi-task learning, a learner is given a collection of prediction tasksand needs to solve all of them. In contrast to previous work, which requiredthat annotated training data is available for all tasks, we consider a newsetting, in which for some tasks, potentially most of them, only unlabeledtraining data is provided. Consequently, to solve all tasks, information mustbe transferred between tasks with labels and tasks without labels. Focusing onan instance-based transfer method we analyze two variants of this setting: whenthe set of labeled tasks is fixed, and when it can be actively selected by thelearner. We state and prove a generalization bound that covers both scenariosand derive from it an algorithm for making the choice of labeled tasks (in theactive case) and for transferring information between the tasks in a principledway. We also illustrate the effectiveness of the algorithm by experiments onsynthetic and real data.

Multi-Task Learning with Labeled and Unlabeled Tasks