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

Analogy-making between narratives is crucial for human reasoning. In thispaper, we evaluate the ability to identify and generate analogies byconstructing a first-of-its-kind large-scale story-level analogy corpus,\textsc{StoryAnalogy}, which contains 24K story pairs from diverse domains withhuman annotations on two similarities from the extended Structure-MappingTheory. We design a set of tests on \textsc{StoryAnalogy}, presenting the firstevaluation of story-level analogy identification and generation. Interestingly,we find that the analogy identification tasks are incredibly difficult not onlyfor sentence embedding models but also for the recent large language models(LLMs) such as ChatGPT and LLaMa. ChatGPT, for example, only achieved around30% accuracy in multiple-choice questions (compared to over 85% accuracy forhumans). Furthermore, we observe that the data in \textsc{StoryAnalogy} canimprove the quality of analogy generation in LLMs, where a fine-tunedFlanT5-xxl model achieves comparable performance to zero-shot ChatGPT.

StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding