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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Topic models such as LDA, DocNADE, iDocNADEe have been popular in documentanalysis. However, the traditional topic models have several limitationsincluding: (1) Bag-of-words (BoW) assumption, where they ignore word ordering,(2) Data sparsity, where the application of topic models is challenging due tolimited word co-occurrences, leading to incoherent topics and (3) No ContinuousLearning framework for topic learning in lifelong fashion, exploitinghistorical knowledge (or latent topics) and minimizing catastrophic forgetting.This thesis focuses on addressing the above challenges within neural topicmodeling framework. We propose: (1) Contextualized topic model that combines atopic and a language model and introduces linguistic structures (such as wordordering, syntactic and semantic features, etc.) in topic modeling, (2) A novellifelong learning mechanism into neural topic modeling framework to demonstratecontinuous learning in sequential document collections and minimizingcatastrophic forgetting. Additionally, we perform a selective data augmentationto alleviate the need for complete historical corpora during data hallucinationor replay.

Lifelong Neural Topic Learning in Contextualized Autoregressive Topic Models of Language via Informative Transfers