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

We present an approach to interactive-predictive neural machine translationthat attempts to reduce human effort from three directions: Firstly, instead ofrequiring humans to select, correct, or delete segments, we employ the idea oflearning from human reinforcements in form of judgments on the quality ofpartial translations. Secondly, human effort is further reduced by using theentropy of word predictions as uncertainty criterion to trigger feedbackrequests. Lastly, online updates of the model parameters after everyinteraction allow the model to adapt quickly. We show in simulation experimentsthat reward signals on partial translations significantly improve characterF-score and BLEU compared to feedback on full translations only, while humaneffort can be reduced to an average number of $5$ feedback requests for everyinput.

A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation