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

Commonsense Knowledge Base (CSKB) Population aims at reasoning over unseenentities and assertions on CSKBs, and is an important yet hard commonsensereasoning task. One challenge is that it requires out-of-domain generalizationability as the source CSKB for training is of a relatively smaller scale (1M)while the whole candidate space for population is way larger (200M). We proposePseudoReasoner, a semi-supervised learning framework for CSKB population thatuses a teacher model pre-trained on CSKBs to provide pseudo labels on theunlabeled candidate dataset for a student model to learn from. The teacher canbe a generative model rather than restricted to discriminative models asprevious works. In addition, we design a new filtering procedure for pseudolabels based on influence function and the student model's prediction tofurther improve the performance. The framework can improve the backbone modelKG-BERT (RoBERTa-large) by 3.3 points on the overall performance andespecially, 5.3 points on the out-of-domain performance, and achieves thestate-of-the-art. Codes and data are available athttps://github.com/HKUST-KnowComp/PseudoReasoner.

PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population