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

Most of the information on the Internet is represented in the form ofmicrotexts, which are short text snippets such as news headlines or tweets.These sources of information are abundant, and mining these data could uncovermeaningful insights. Topic modeling is one of the popular methods to extractknowledge from a collection of documents; however, conventional topic modelssuch as latent Dirichlet allocation (LDA) are unable to perform well on shortdocuments, mostly due to the scarcity of word co-occurrence statistics embeddedin the data. The objective of our research is to create a topic model that canachieve great performances on microtexts while requiring a small runtime forscalability to large datasets. To solve the lack of information of microtexts,we allow our method to take advantage of word embeddings for additionalknowledge of relationships between words. For speed and scalability, we applyautoencoding variational Bayes, an algorithm that can perform efficientblack-box inference in probabilistic models. The result of our work is a noveltopic model called the nested variational autoencoder, which is a distributionthat takes into account word vectors and is parameterized by a neural networkarchitecture. For optimization, the model is trained to approximate theposterior distribution of the original LDA model. Experiments show theimprovements of our model on microtexts as well as its runtime advantage.

Nested Variational Autoencoder for Topic Modeling on Microtexts with Word Vectors