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

Machine-based prediction of real-world events is garnering attention due toits potential for informed decision-making. Whereas traditional forecastingpredominantly hinges on structured data like time-series, recent breakthroughsin language models enable predictions using unstructured text. In particular,(Zou et al., 2022) unveils AutoCast, a new benchmark that employs news articlesfor answering forecasting queries. Nevertheless, existing methods still trailbehind human performance. The cornerstone of accurate forecasting, we argue,lies in identifying a concise, yet rich subset of news snippets from a vastcorpus. With this motivation, we introduce AutoCast++, a zero-shotranking-based context retrieval system, tailored to sift through expansive newsdocument collections for event forecasting. Our approach first re-ranksarticles based on zero-shot question-passage relevance, honing in onsemantically pertinent news. Following this, the chosen articles are subjectedto zero-shot summarization to attain succinct context. Leveraging a pre-trainedlanguage model, we conduct both the relevance evaluation and articlesummarization without needing domain-specific training. Notably, recentarticles can sometimes be at odds with preceding ones due to new facts orunanticipated incidents, leading to fluctuating temporal dynamics. To tacklethis, our re-ranking mechanism gives preference to more recent articles, and wefurther regularize the multi-passage representation learning to align withhuman forecaster responses made on different dates. Empirical resultsunderscore marked improvements across multiple metrics, improving theperformance for multiple-choice questions (MCQ) by 48% and true/false (TF)questions by up to 8%.

AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval