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

Recent advances in machine translation (MT) have shown that Minimum BayesRisk (MBR) decoding can be a powerful alternative to beam search decoding,especially when combined with neural-based utility functions. However, theperformance of MBR decoding depends heavily on how and how many candidates aresampled from the model. In this paper, we explore how different samplingapproaches for generating candidate lists for MBR decoding affect performance.We evaluate popular sampling approaches, such as ancestral, nucleus, and top-ksampling. Based on our insights into their limitations, we experiment with therecently proposed epsilon-sampling approach, which prunes away all tokens witha probability smaller than epsilon, ensuring that each token in a samplereceives a fair probability mass. Through extensive human evaluations, wedemonstrate that MBR decoding based on epsilon-sampling significantlyoutperforms not only beam search decoding, but also MBR decoding with all othertested sampling methods across four language pairs.

Epsilon Sampling Rocks: Investigating Sampling Strategies for Minimum Bayes Risk Decoding for Machine Translation