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

In this paper, we present an approach to learn multilingual sentenceembeddings using a bi-directional dual-encoder with additive margin softmax.The embeddings are able to achieve state-of-the-art results on the UnitedNations (UN) parallel corpus retrieval task. In all the languages tested, thesystem achieves P@1 of 86% or higher. We use pairs retrieved by our approach totrain NMT models that achieve similar performance to models trained on goldpairs. We explore simple document-level embeddings constructed by averaging oursentence embeddings. On the UN document-level retrieval task, documentembeddings achieve around 97% on P@1 for all experimented language pairs.Lastly, we evaluate the proposed model on the BUCC mining task. The learnedembeddings with raw cosine similarity scores achieve competitive resultscompared to current state-of-the-art models, and with a second-stage scorer weachieve a new state-of-the-art level on this task.

Improving Multilingual Sentence Embedding using Bi-directional Dual Encoder with Additive Margin Softmax