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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Explicit decomposition modeling, which involves breaking down complex tasksinto more straightforward and often more interpretable sub-tasks, has long beena central theme in developing robust and interpretable NLU systems. However,despite the many datasets and resources built as part of this effort, themajority have small-scale annotations and limited scope, which is insufficientto solve general decomposition tasks. In this paper, we look at large-scaleintermediate pre-training of decomposition-based transformers using distantsupervision from comparable texts, particularly large-scale parallel news. Weshow that with such intermediate pre-training, developing robustdecomposition-based models for a diverse range of tasks becomes more feasible.For example, on semantic parsing, our model, DecompT5, improves 20% to 30% ontwo datasets, Overnight and TORQUE, over the baseline language model. Wefurther use DecompT5 to build a novel decomposition-based QA system namedDecompEntail, improving over state-of-the-art models, including GPT-3, on bothHotpotQA and StrategyQA by 8% and 4%, respectively.

Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts