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

Representing documents into high dimensional embedding space while preservingthe structural similarity between document sources has been an ultimate goalfor many works on text representation learning. Current embedding models,however, mainly rely on the availability of label supervision to increase theexpressiveness of the resulting embeddings. In contrast, unsupervisedembeddings are cheap, but they often cannot capture implicit structure intarget corpus, particularly for samples that come from different distributionwith the pretraining source.  Our study aims to loosen up the dependency on label supervision by learningdocument embeddings via Sequence-to-Sequence (Seq2Seq) text generator.Specifically, we reformulate keyphrase generation task into multi-label keywordgeneration in community-based Question Answering (cQA). Our empirical resultsshow that KeyGen2Vec in general is superior than multi-label keyword classifierby up to 14.7% based on Purity, Normalized Mutual Information (NMI), andF1-Score metrics. Interestingly, although in general the absolute advantage oflearning embeddings through label supervision is highly positive acrossevaluation datasets, KeyGen2Vec is shown to be competitive with classifier thatexploits topic label supervision in Yahoo! cQA with larger number of latenttopic labels.

KeyGen2Vec: Learning Document Embedding via Multi-label Keyword Generation in Question-Answering