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

Topic models have been widely used in discovering latent topics which areshared across documents in text mining. Vector representations, word embeddingsand topic embeddings, map words and topics into a low-dimensional and densereal-value vector space, which have obtained high performance in NLP tasks.However, most of the existing models assume the result trained by one of themare perfect correct and used as prior knowledge for improving the other model.Some other models use the information trained from external large corpus tohelp improving smaller corpus. In this paper, we aim to build such an algorithmframework that makes topic models and vector representations mutually improveeach other within the same corpus. An EM-style algorithm framework is employedto iteratively optimize both topic model and vector representations.Experimental results show that our model outperforms state-of-art methods onvarious NLP tasks.

LTSG: Latent Topical Skip-Gram for Mutually Learning Topic Model and Vector Representations