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

Neural machine translation (NMT) typically adopts the encoder-decoderframework. A good understanding of the characteristics and functionalities ofthe encoder and decoder can help to explain the pros and cons of the framework,and design better models for NMT. In this work, we conduct an empirical studyon the encoder and the decoder in NMT, taking Transformer as an example. Wefind that 1) the decoder handles an easier task than the encoder in NMT, 2) thedecoder is more sensitive to the input noise than the encoder, and 3) thepreceding words/tokens in the decoder provide strong conditional information,which accounts for the two observations above. We hope those observations canshed light on the characteristics of the encoder and decoder and inspire futureresearch on NMT.

Hard but Robust, Easy but Sensitive: How Encoder and Decoder Perform in Neural Machine Translation