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

The scientific claim verification task requires an NLP system to labelscientific documents which Support or Refute an input claim, and to selectevidentiary sentences (or rationales) justifying each predicted label. In thiswork, we present MultiVerS, which predicts a fact-checking label and identifiesrationales in a multitask fashion based on a shared encoding of the claim andfull document context. This approach accomplishes two key modeling goals.First, it ensures that all relevant contextual information is incorporated intoeach labeling decision. Second, it enables the model to learn from instancesannotated with a document-level fact-checking label, but lacking sentence-levelrationales. This allows MultiVerS to perform weakly-supervised domainadaptation by training on scientific documents labeled using high-precisionheuristics. Our approach outperforms two competitive baselines on threescientific claim verification datasets, with particularly strong performance inzero / few-shot domain adaptation experiments. Our code and data are availableat https://github.com/dwadden/multivers.

MultiVerS: Improving scientific claim verification with weak supervision and full-document context