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

Few-shot table-to-text generation is a task of composing fluent and faithfulsentences to convey table content using limited data. Despite many effortshaving been made towards generating impressive fluent sentences by fine-tuningpowerful pre-trained language models, the faithfulness of generated contentstill needs to be improved. To this end, this paper proposes a novel approachAttend, Memorize and Generate (called AMG), inspired by the text generationprocess of humans. In particular, AMG (1) attends over the multi-granularity ofcontext using a novel strategy based on table slot level and traditionaltoken-by-token level attention to exploit both the table structure and naturallinguistic information; (2) dynamically memorizes the table slot allocationstates; and (3) generates faithful sentences according to both the context andmemory allocation states. Comprehensive experiments with human evaluation onthree domains (i.e., humans, songs, and books) of the Wiki dataset show thatour model can generate higher qualified texts when compared with severalstate-of-the-art baselines, in both fluency and faithfulness.

Attend, Memorize and Generate: Towards Faithful Table-to-Text Generation in Few Shots