Pre-train, Prompt, and Recommendation: A Comprehensive Survey of Language Modeling Paradigm Adaptations in Recommender Systems
Year: 2023
Type: article
Abstract: The emergence of Pre-trained Language Models (PLMs) has achieved tremendous success in the field of Natural Language Processing (NLP) by learning universal representations on large corpora in a self-supervised manner. The pre-trained models and the learned representations can be beneficial to a series of downstream NLP tasks. This training paradigm has recently been adapted to the recommendation domain and is considered a promising approach by both academia and industry. In this paper, we systematically investigate how to extract and transfer knowledge from pre-trained models learned by different PLM-related training paradigms to improve recommendation performance from various perspectives, such as generality, sparsity, efficiency and effectiveness. Specifically, we propose a comprehensive taxonomy to divide existing PLM-based recommender systems w.r.t. their training strategies and objectives. Then, we analyze and summarize the connection between PLM-based training paradigms and different input data types for recommender systems. Finally, we elaborate on open issues and future research directions in this vibrant field.
DOI: 10.1162/tacl_a_00619
Authors: Peng Liu, Lemei Zhang, Jon Atle Gulla
Institution: Norwegian University of Science and Technology
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
Funder: Norges Forskningsråd
Award: G2589906563
OpenAlex ID: W4389777839
