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 NMT we search for the mode of the model distribution to form predictions.The mode and other high-probability translations found by beam search have beenshown to often be inadequate in a number of ways. This prevents improvingtranslation quality through better search, as these idiosyncratic translationsend up selected by the decoding algorithm, a problem known as the beam searchcurse. Recently, an approximation to minimum Bayes risk (MBR) decoding has beenproposed as an alternative decision rule that would likely not suffer from thesame problems. We analyse this approximation and establish that it has noequivalent to the beam search curse. We then design approximations thatdecouple the cost of exploration from the cost of robust estimation of expectedutility. This allows for much larger hypothesis spaces, which we show to bebeneficial. We also show that mode-seeking strategies can aid in constructingcompact sets of promising hypotheses and that MBR is effective in identifyinggood translations in them. We conduct experiments on three language pairsvarying in amounts of resources available: English into and from German,Romanian, and Nepali.

Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation