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

Though offering amazing contextualized token-level representations, currentpre-trained language models take less attention on accurately acquiringsentence-level representation during their self-supervised pre-training.However, contrastive objectives which dominate the current sentencerepresentation learning bring little linguistic interpretability and noperformance guarantee on downstream semantic tasks. We instead propose a novelgenerative self-supervised learning objective based on phrase reconstruction.To overcome the drawbacks of previous generative methods, we carefully modelintra-sentence structure by breaking down one sentence into pieces of importantphrases. Empirical studies show that our generative learning achieves powerfulenough performance improvement and outperforms the current state-of-the-artcontrastive methods not only on the STS benchmarks, but also on downstreamsemantic retrieval and reranking tasks. Our code is available athttps://github.com/chengzhipanpan/PaSeR.

Sentence Representation Learning with Generative Objective rather than Contrastive Objective