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

Language models trained on large-scale corpora can generate remarkably fluentresults in open-domain dialogue. However, for the persona-based dialoguegeneration task, consistency and coherence are also key factors, which aregreat challenges for language models. Existing works mainly focus on valuabledata filtering, model structure modifying, or objective function designing,while their improvements are limited and hard to generalize to all types ofpre-trained language models. However, we find that language models can produceconsistent and coherent responses if we consider enough generations. Thus, theproblems lay in large-scale response generation and target response selection.In this work, a simple but effective two-stage SimOAP strategy is proposed,i.e., over-sampling and post-evaluation. The over-sampling stage takeslarge-scale responses from existing trained models efficiently viaoff-the-shelf distilling and compressing methods, and the post-evaluation stageselects a good response based on multiple well-designed evaluation metrics fromlarge-scale candidates. Experimental results show that the proposed plug-inSimOAP strategy improves the backbone models and outperforms the baselinestrategies in both automatic and human evaluations.

SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation