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 emergence of Pre-trained Language Models (PLMs) has achieved tremendoussuccess in the field of Natural Language Processing (NLP) by learning universalrepresentations on large corpora in a self-supervised manner. The pre-trainedmodels and the learned representations can be beneficial to a series ofdownstream NLP tasks. This training paradigm has recently been adapted to therecommendation domain and is considered a promising approach by both academiaand industry. In this paper, we systematically investigate how to extract andtransfer knowledge from pre-trained models learned by different PLM-relatedtraining paradigms to improve recommendation performance from variousperspectives, such as generality, sparsity, efficiency and effectiveness.Specifically, we propose a comprehensive taxonomy to divide existing PLM-basedrecommender systems w.r.t. their training strategies and objectives. Then, weanalyze and summarize the connection between PLM-based training paradigms anddifferent input data types for recommender systems. Finally, we elaborate onopen issues and future research directions in this vibrant field.

Pre-train, Prompt and Recommendation: A Comprehensive Survey of Language Modelling Paradigm Adaptations in Recommender Systems