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

In many machine learning scenarios, supervision by gold labels is notavailable and consequently neural models cannot be trained directly by maximumlikelihood estimation (MLE). In a weak supervision scenario, metric-augmentedobjectives can be employed to assign feedback to model outputs, which can beused to extract a supervision signal for training. We present severalobjectives for two separate weakly supervised tasks, machine translation andsemantic parsing. We show that objectives should actively discourage negativeoutputs in addition to promoting a surrogate gold structure. This notion ofbipolarity is naturally present in ramp loss objectives, which we adapt toneural models. We show that bipolar ramp loss objectives outperform othernon-bipolar ramp loss objectives and minimum risk training (MRT) on both weaklysupervised tasks, as well as on a supervised machine translation task.Additionally, we introduce a novel token-level ramp loss objective, which isable to outperform even the best sequence-level ramp loss on both weaklysupervised tasks.

Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss