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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Natural language is inherently a discrete symbolic representation of humanknowledge. Recent advances in machine learning (ML) and in natural languageprocessing (NLP) seem to contradict the above intuition: discrete symbols arefading away, erased by vectors or tensors called distributed and distributionalrepresentations. However, there is a strict link betweendistributed/distributional representations and discrete symbols, being thefirst an approximation of the second. A clearer understanding of the strictlink between distributed/distributional representations and symbols maycertainly lead to radically new deep learning networks. In this paper we make asurvey that aims to renew the link between symbolic representations anddistributed/distributional representations. This is the right time torevitalize the area of interpreting how discrete symbols are represented insideneural networks.

Symbolic, Distributed and Distributional Representations for Natural Language Processing in the Era of Deep Learning: a Survey