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

In open domain table-to-text generation, we notice that the unfaithfulgeneration usually contains hallucinated content which can not be aligned toany input table record. We thus try to evaluate the generation faithfulnesswith two entity-centric metrics: table record coverage and the ratio ofhallucinated entities in text, both of which are shown to have strong agreementwith human judgements. Then based on these metrics, we quantitatively analyzethe correlation between training data quality and generation fidelity whichindicates the potential usage of entity information in faithful generation.Motivated by these findings, we propose two methods for faithful generation: 1)augmented training by incorporating the auxiliary entity information, includingboth an augmented plan-based model and an unsupervised model and 2) traininginstance selection based on faithfulness ranking. We show these approachesimprove generation fidelity in both full dataset setting and few shot learningsettings by both automatic and human evaluations.

Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View