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

Unsupervised sentence embeddings learning has been recently dominated bycontrastive learning methods (e.g., SimCSE), which keep positive pairs similarand push negative pairs apart. The contrast operation aims to keep as muchinformation as possible by maximizing the mutual information between positiveinstances, which leads to redundant information in sentence embedding. Toaddress this problem, we present an information minimization based contrastivelearning (InforMin-CL) model to retain the useful information and discard theredundant information by maximizing the mutual information and minimizing theinformation entropy between positive instances meanwhile for unsupervisedsentence representation learning. Specifically, we find that informationminimization can be achieved by simple contrast and reconstruction objectives.The reconstruction operation reconstitutes the positive instance via the otherpositive instance to minimize the information entropy between positiveinstances. We evaluate our model on fourteen downstream tasks, including bothsupervised and unsupervised (semantic textual similarity) tasks. Extensiveexperimental results show that our InforMin-CL obtains a state-of-the-artperformance.

An Information Minimization Based Contrastive Learning Model for Unsupervised Sentence Embeddings Learning