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

The ability to take into account the characteristics - also called features -of observations is essential in Natural Language Processing (NLP) problems.Hidden Markov Chain (HMC) model associated with classic Forward-Backwardprobabilities cannot handle arbitrary features like prefixes or suffixes of anysize, except with an independence condition. For twenty years, this default hasencouraged the development of other sequential models, starting with theMaximum Entropy Markov Model (MEMM), which elegantly integrates arbitraryfeatures. More generally, it led to neglect HMC for NLP. In this paper, we showthat the problem is not due to HMC itself, but to the way its restorationalgorithms are computed. We present a new way of computing HMC basedrestorations using original Entropic Forward and Entropic Backward (EFB)probabilities. Our method allows taking into account features in the HMCframework in the same way as in the MEMM framework. We illustrate theefficiency of HMC using EFB in Part-Of-Speech Tagging, showing its superiorityover MEMM based restoration. We also specify, as a perspective, how HMCs withEFB might appear as an alternative to Recurrent Neural Networks to treatsequential data with a deep architecture.

Hidden Markov Chains, Entropic Forward-Backward, and Part-Of-Speech Tagging