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

Natural Language Inference (NLI) has been extensively studied by the NLPcommunity as a framework for estimating the semantic relation between sentencepairs. While early work identified certain biases in NLI models, recentadvancements in modeling and datasets demonstrated promising performance. Inthis work, we further explore the direct zero-shot applicability of NLI modelsto real applications, beyond the sentence-pair setting they were trained on.First, we analyze the robustness of these models to longer and out-of-domaininputs. Then, we develop new aggregation methods to allow operating over fulldocuments, reaching state-of-the-art performance on the ContractNLI dataset.Interestingly, we find NLI scores to provide strong retrieval signals, leadingto more relevant evidence extractions compared to common similarity-basedmethods. Finally, we go further and investigate whole document clusters toidentify both discrepancies and consensus among sources. In a test case, wefind real inconsistencies between Wikipedia pages in different languages aboutthe same topic.

Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusters