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

Measuring Sentence Textual Similarity (STS) is a classic task that can beapplied to many downstream NLP applications such as text generation andretrieval. In this paper, we focus on unsupervised STS that works on variousdomains but only requires minimal data and computational resources.Theoretically, we propose a light-weighted Expectation-Correction (EC)formulation for STS computation. EC formulation unifies unsupervised STSapproaches including the cosine similarity of Additively Composed (AC) sentenceembeddings, Optimal Transport (OT), and Tree Kernels (TK). Moreover, we proposethe Recursive Optimal Transport Similarity (ROTS) algorithm to capture thecompositional phrase semantics by composing multiple recursive EC formulations.ROTS finishes in linear time and is faster than its predecessors. ROTS isempirically more effective and scalable than previous approaches. Extensiveexperiments on 29 STS tasks under various settings show the clear advantage ofROTS over existing approaches. Detailed ablation studies demonstrate theeffectiveness of our approaches.

Unsupervised Sentence Textual Similarity with Compositional Phrase Semantics