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

Counterfactually-Augmented Data (CAD) -- minimal editing of sentences to flipthe corresponding labels -- has the potential to improve theOut-Of-Distribution (OOD) generalization capability of language models, as CADinduces language models to exploit domain-independent causal features andexclude spurious correlations. However, the empirical results of CAD's OODgeneralization are not as efficient as anticipated. In this study, we attributethe inefficiency to the myopia phenomenon caused by CAD: language models onlyfocus on causal features that are edited in the augmentation operation andexclude other non-edited causal features. Therefore, the potential of CAD isnot fully exploited. To address this issue, we analyze the myopia phenomenon infeature space from the perspective of Fisher's Linear Discriminant, then weintroduce two additional constraints based on CAD's structural properties(dataset-level and sentence-level) to help language models extract morecomplete causal features in CAD, thereby mitigating the myopia phenomenon andimproving OOD generalization capability. We evaluate our method on two tasks:Sentiment Analysis and Natural Language Inference, and the experimental resultsdemonstrate that our method could unlock the potential of CAD and improve theOOD generalization performance of language models by 1.0% to 5.9%.

Unlock the Potential of Counterfactually-Augmented Data in Out-Of-Distribution Generalization