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

Reasoning over commonsense knowledge bases (CSKB) whose elements are in theform of free-text is an important yet hard task in NLP. While CSKB completiononly fills the missing links within the domain of the CSKB, CSKB population isalternatively proposed with the goal of reasoning unseen assertions fromexternal resources. In this task, CSKBs are grounded to a large-scaleeventuality (activity, state, and event) graph to discriminate whether noveltriples from the eventuality graph are plausible or not. However, existingevaluations on the population task are either not accurate (automaticevaluation with randomly sampled negative examples) or of small scale (humanannotation). In this paper, we benchmark the CSKB population task with a newlarge-scale dataset by first aligning four popular CSKBs, and then presenting ahigh-quality human-annotated evaluation set to probe neural models' commonsensereasoning ability. We also propose a novel inductive commonsense reasoningmodel that reasons over graphs. Experimental results show that generalizingcommonsense reasoning on unseen assertions is inherently a hard task. Modelsachieving high accuracy during training perform poorly on the evaluation set,with a large gap between human performance. We will make the data publiclyavailable for future contributions. Codes and data are available athttps://github.com/HKUST-KnowComp/CSKB-Population.

Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset