Zero-Shot Recommendation as Language Modeling - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Zero-Shot Recommendation as Language Modeling

Résumé

Recommendation is the task of ranking items (e.g. movies or products) according to individual user needs. Current systems rely on collaborative filtering and content-based techniques, which both require structured training data. We propose a framework for recommendation with off-the-shelf pretrained language models (LM) that only used unstructured text corpora as training data. If a user u liked Matrix and Inception, we construct a textual prompt, e.g. "Movies like Matrix, Inception, " to estimate the affinity between u and m with LM likelihood. We motivate our idea with a corpus analysis, evaluate several prompt structures, and we compare LM-based recommendation with standard matrix factorization trained on different data regimes. The code for our experiments is publicly available 1 .
Fichier principal
Vignette du fichier
Zero-Shot_Recommendation_as_Language_Modeling.pdf (258.63 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04068708 , version 1 (14-04-2023)

Identifiants

Citer

Damien Sileo, Wout Vossen, Robbe Raymaekers. Zero-Shot Recommendation as Language Modeling. ECIR 2022 - 44th European Conference on IR Research, Apr 2022, Stavanger, Norway. pp.223-230, ⟨10.1007/978-3-030-99739-7_26⟩. ⟨hal-04068708⟩
29 Consultations
9 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More