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

Data augmentations (DA) are the cores to achieving robustsequence-to-sequence learning on various natural language processing (NLP)tasks. However, most of the DA approaches force the decoder to make predictionsconditioned on the perturbed input representation, underutilizing supervisedinformation provided by perturbed input. In this work, we propose aframework-level robust sequence-to-sequence learning approach, named BLISS, viaself-supervised input representation, which has the great potential tocomplement the data-level augmentation approaches. The key idea is to supervisethe sequence-to-sequence framework with both the \textit{supervised}("input$\rightarrow$output") and \textit{self-supervised} ("perturbedinput$\rightarrow$input") information. We conduct comprehensive experiments tovalidate the effectiveness of BLISS on various tasks, including machinetranslation, grammatical error correction, and text summarization. The resultsshow that BLISS outperforms significantly the vanilla Transformer andconsistently works well across tasks than the other five contrastive baselines.Extensive analyses reveal that BLISS learns robust representations and richlinguistic knowledge, confirming our claim. Source code will be released uponpublication.

BLISS: Robust Sequence-to-Sequence Learning via Self-Supervised Input Representation