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

Humans can effortlessly understand the coordinate structure of sentences suchas "Niels Bohr and Kurt Cobain were born in Copenhagen and Seattle,respectively". In the context of natural language inference (NLI), we examinehow language models (LMs) reason with respective readings (Gawron and Kehler,2004) from two perspectives: syntactic-semantic and commonsense-worldknowledge. We propose a controlled synthetic dataset WikiResNLI and a naturallyoccurring dataset NatResNLI to encompass various explicit and implicitrealizations of "respectively". We show that fine-tuned NLI models strugglewith understanding such readings without explicit supervision. While few-shotlearning is easy in the presence of explicit cues, longer training is requiredwhen the reading is evoked implicitly, leaving models to rely on common senseinferences. Furthermore, our fine-grained analysis indicates models fail togeneralize across different constructions. To conclude, we demonstrate that LMsstill lag behind humans in generalizing to the long tail of linguisticconstructions.

What does the Failure to Reason with "Respectively" in Zero/Few-Shot Settings Tell Us about Language Models?