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 word embeddings and topics are complementary representations, severalpast works have only used pre-trained word embeddings in (neural) topicmodeling to address data sparsity problem in short text or small collection ofdocuments. However, no prior work has employed (pre-trained latent) topics intransfer learning paradigm. In this paper, we propose an approach to (1)perform knowledge transfer using latent topics obtained from a large sourcecorpus, and (2) jointly transfer knowledge via the two representations (orviews) in neural topic modeling to improve topic quality, better deal withpolysemy and data sparsity issues in a target corpus. In doing so, we firstaccumulate topics and word representations from one or many source corpora tobuild a pool of topics and word vectors. Then, we identify one or multiplerelevant source domain(s) and take advantage of corresponding topics and wordfeatures via the respective pools to guide meaningful learning in the sparsetarget domain. We quantify the quality of topic and document representationsvia generalization (perplexity), interpretability (topic coherence) andinformation retrieval (IR) using short-text, long-text, small and largedocument collections from news and medical domains. We have demonstrated thestate-of-the-art results on topic modeling with the proposed framework.

Multi-view and Multi-source Transfers in Neural Topic Modeling with Pretrained Topic and Word Embeddings