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

Although the problem of hallucinations in neural machine translation (NMT)has received some attention, research on this highly pathological phenomenonlacks solid ground. Previous work has been limited in several ways: it oftenresorts to artificial settings where the problem is amplified, it disregardssome (common) types of hallucinations, and it does not validate adequacy ofdetection heuristics. In this paper, we set foundations for the study of NMThallucinations. First, we work in a natural setting, i.e., in-domain datawithout artificial noise neither in training nor in inference. Next, weannotate a dataset of over 3.4k sentences indicating different kinds ofcritical errors and hallucinations. Then, we turn to detection methods and bothrevisit methods used previously and propose using glass-box uncertainty-baseddetectors. Overall, we show that for preventive settings, (i) previously usedmethods are largely inadequate, (ii) sequence log-probability works best andperforms on par with reference-based methods. Finally, we proposeDeHallucinator, a simple method for alleviating hallucinations at test timethat significantly reduces the hallucinatory rate. To ease future research, werelease our annotated dataset for WMT18 German-English data, along with themodel, training data, and code.

Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation