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

Learning multi-lingual sentence embeddings is a fundamental and significanttask in natural language processing. Recent trends of learning bothmono-lingual and multi-lingual sentence embeddings are mainly based oncontrastive learning (CL) with an anchor, one positive, and multiple negativeinstances. In this work, we argue that leveraging multiple positives should beconsidered for multi-lingual sentence embeddings because (1) positives in adiverse set of languages can benefit cross-lingual learning, and (2) transitivesimilarity across multiple positives can provide reliable structuralinformation to learn. In order to investigate the impact of CL with multiplepositives, we propose a novel approach MPCL to effectively utilize multiplepositive instances to improve learning multi-lingual sentence embeddings. Ourexperimental results on various backbone models and downstream tasks supportthat compared with conventional CL, MPCL leads to better retrieval, semanticsimilarity, and classification performances. We also observe that on unseenlanguages, sentence embedding models trained on multiple positives have bettercross-lingual transferring performance than models trained on a single positiveinstance.

Leveraging Multi-lingual Positive Instances in Contrastive Learning to Improve Sentence Embedding