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

Encoder-decoder architecture is widely adopted for sequence-to-sequencemodeling tasks. For machine translation, despite the evolution from longshort-term memory networks to Transformer networks, plus the introduction anddevelopment of attention mechanism, encoder-decoder is still the de factoneural network architecture for state-of-the-art models. While the motivationfor decoding information from some hidden space is straightforward, the strictseparation of the encoding and decoding steps into an encoder and a decoder inthe model architecture is not necessarily a must. Compared to the task ofautoregressive language modeling in the target language, machine translationsimply has an additional source sentence as context. Given the fact that neurallanguage models nowadays can already handle rather long contexts in the targetlanguage, it is natural to ask whether simply concatenating the source andtarget sentences and training a language model to do translation would work. Inthis work, we investigate the aforementioned concept for machine translation.Specifically, we experiment with bilingual translation, translation withadditional target monolingual data, and multilingual translation. In all cases,this alternative approach performs on par with the baseline encoder-decoderTransformer, suggesting that an encoder-decoder architecture might be redundantfor neural machine translation.

Is Encoder-Decoder Redundant for Neural Machine Translation?