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

Words of estimative probability (WEP) are expressions of a statement'splausibility (probably, maybe, likely, doubt, likely, unlikely, impossible...).Multiple surveys demonstrate the agreement of human evaluators when assigningnumerical probability levels to WEP. For example, highly likely corresponds toa median chance of 0.90+-0.08 in Fagen-Ulmschneider (2015)'s survey. In thiswork, we measure the ability of neural language processing models to capturethe consensual probability level associated to each WEP. Firstly, we use theUNLI dataset (Chen et al., 2020) which associates premises and hypotheses withtheir perceived joint probability p, to construct prompts, e.g. "[PREMISE].[WEP], [HYPOTHESIS]." and assess whether language models can predict whetherthe WEP consensual probability level is close to p. Secondly, we construct adataset of WEP-based probabilistic reasoning, to test whether language modelscan reason with WEP compositions. When prompted "[EVENTA] is likely. [EVENTB]is impossible.", a causal language model should not express that [EVENTA&B] islikely. We show that both tasks are unsolved by off-the-shelf English languagemodels, but that fine-tuning leads to transferable improvement.

Probing neural language models for understanding of words of estimative probability