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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Humans can classify data of an unseen category by reasoning on its languageexplanations. This ability is owing to the compositional nature of language: wecan combine previously seen attributes to describe the new category. Forexample, we might describe a sage thrasher as "it has a slim straightrelatively short bill, yellow eyes and a long tail", so that others can usetheir knowledge of attributes "slim straight relatively short bill", "yelloweyes" and "long tail" to recognize a sage thrasher. Inspired by thisobservation, in this work we tackle zero-shot classification task by logicallyparsing and reasoning on natural language expla-nations. To this end, wepropose the framework CLORE (Classification by LOgical Reasoning onExplanations). While previous methods usually regard textual information asimplicit features, CLORE parses explanations into logical structures and thenexplicitly reasons along thess structures on the input to produce aclassification score. Experimental results on explanation-based zero-shotclassification benchmarks demonstrate that CLORE is superior to baselines,which we further show mainly comes from higher scores on tasks requiring morelogical reasoning. We also demonstrate that our framework can be extended tozero-shot classification on visual modality. Alongside classificationdecisions, CLORE can provide the logical parsing and reasoning process as aclear form of rationale. Through empirical analysis we demonstrate that CLOREis also less affected by linguistic biases than baselines.

Zero-Shot Classification by Logical Reasoning on Natural Language Explanations