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

The last decade has witnessed enormous improvements in science andtechnology, stimulating the growing demand for economic and cultural exchangesin various countries. Building a neural machine translation (NMT) system hasbecome an urgent trend, especially in the low-resource setting. However, recentwork tends to study NMT systems for low-resource languages centered on English,while few works focus on low-resource NMT systems centered on other languagessuch as Chinese. To achieve this, the low-resource multilingual translationchallenge of the 2021 iFLYTEK AI Developer Competition provides theChinese-centric multilingual low-resource NMT tasks, where participants arerequired to build NMT systems based on the provided low-resource samples. Inthis paper, we present the winner competition system that leverages monolingualword embeddings data enhancement, bilingual curriculum learning, andcontrastive re-ranking. In addition, a new Incomplete-Trust (In-trust) lossfunction is proposed to replace the traditional cross-entropy loss whentraining. The experimental results demonstrate that the implementation of theseideas leads better performance than other state-of-the-art methods. All theexperimental codes are released at:https://github.com/WENGSYX/Low-resource-text-translation.

Towards Better Chinese-centric Neural Machine Translation for Low-resource Languages