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

We address two challenges of probabilistic topic modelling in order to betterestimate the probability of a word in a given context, i.e., P(word|context):(1) No Language Structure in Context: Probabilistic topic models ignore wordorder by summarizing a given context as a "bag-of-word" and consequently thesemantics of words in the context is lost. The LSTM-LM learns a vector-spacerepresentation of each word by accounting for word order in local collocationpatterns and models complex characteristics of language (e.g., syntax andsemantics), while the TM simultaneously learns a latent representation from theentire document and discovers the underlying thematic structure. We unite twocomplementary paradigms of learning the meaning of word occurrences bycombining a TM (e.g., DocNADE) and a LM in a unified probabilistic framework,named as ctx-DocNADE. (2) Limited Context and/or Smaller training corpus ofdocuments: In settings with a small number of word occurrences (i.e., lack ofcontext) in short text or data sparsity in a corpus of few documents, theapplication of TMs is challenging. We address this challenge by incorporatingexternal knowledge into neural autoregressive topic models via a languagemodelling approach: we use word embeddings as input of a LSTM-LM with the aimto improve the word-topic mapping on a smaller and/or short-text corpus. Theproposed DocNADE extension is named as ctx-DocNADEe.  We present novel neural autoregressive topic model variants coupled withneural LMs and embeddings priors that consistently outperform state-of-the-artgenerative TMs in terms of generalization (perplexity), interpretability (topiccoherence) and applicability (retrieval and classification) over 6 long-textand 8 short-text datasets from diverse domains.

textTOvec: Deep Contextualized Neural Autoregressive Topic Models of Language with Distributed Compositional Prior