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

One approach to matching texts from asymmetrical domains is projecting theinput sequences into a common semantic space as feature vectors upon which thematching function can be readily defined and learned. In real-world matchingpractices, it is often observed that with the training goes on, the featurevectors projected from different domains tend to be indistinguishable. Thephenomenon, however, is often overlooked in existing matching models. As aresult, the feature vectors are constructed without any regularization, whichinevitably increases the difficulty of learning the downstream matchingfunctions. In this paper, we propose a novel match method tailored for textmatching in asymmetrical domains, called WD-Match. In WD-Match, a Wassersteindistance-based regularizer is defined to regularize the features vectorsprojected from different domains. As a result, the method enforces the featureprojection function to generate vectors such that those correspond to differentdomains cannot be easily discriminated. The training process of WD-Matchamounts to a game that minimizes the matching loss regularized by theWasserstein distance. WD-Match can be used to improve different text matchingmethods, by using the method as its underlying matching model. Four populartext matching methods have been exploited in the paper. Experimental resultsbased on four publicly available benchmarks showed that WD-Match consistentlyoutperformed the underlying methods and the baselines.

Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains