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

Logical reasoning is of vital importance to natural language understanding.Previous studies either employ graph-based models to incorporate priorknowledge about logical relations, or introduce symbolic logic into neuralmodels through data augmentation. These methods, however, heavily depend onannotated training data, and thus suffer from over-fitting and poorgeneralization problems due to the dataset sparsity. To address these twoproblems, in this paper, we propose MERIt, a MEta-path guided contrastivelearning method for logical ReasonIng of text, to perform self-supervisedpre-training on abundant unlabeled text data. Two novel strategies serve asindispensable components of our method. In particular, a strategy based onmeta-path is devised to discover the logical structure in natural texts,followed by a counterfactual data augmentation strategy to eliminate theinformation shortcut induced by pre-training. The experimental results on twochallenging logical reasoning benchmarks, i.e., ReClor and LogiQA, demonstratethat our method outperforms the SOTA baselines with significant improvements.

MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoning