Prompt Learning for News Recommendation

Abstract

Some recent \textit{news recommendation} (NR) methods introduce a Pre-trained Language Model (PLM) to encode news representation by following the vanilla pre-train and fine-tune paradigm with carefully-designed recommendation-specific neural networks and objective functions. Due to the inconsistent task objective with that of PLM, we argue that their modeling paradigm has not well exploited the abundant semantic information and linguistic knowledge embedded in the pre-training process. Recently, the pre-train, prompt, and predict paradigm, called \textit{prompt learning}, has achieved many successes in natural language processing domain. In this paper, we make the first trial of this new paradigm to develop a \textit{Prompt Learning for News Recommendation} (Prompt4NR) framework, which transforms the task of predicting whether a user would click a candidate news as a cloze-style mask-prediction task. Specifically, we design a series of prompt templates, including discrete, continuous, and hybrid templates, and construct their corresponding answer spaces to examine the proposed Prompt4NR framework. Furthermore, we use the prompt ensembling to integrate predictions from multiple prompt templates. Extensive experiments on the MIND dataset validate the effectiveness of our Prompt4NR with a set of new benchmark results.

arXiv comment11 pages, 7 figures, 3 tables, SIGIR2023 conference

References in corpus (9)

• Efficient Estimation of Word Representations in Vector Space
• Decoupled Weight Decay Regularization
• Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
• NPA: Neural News Recommendation with Personalized Attention
• P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks
• DKN: Deep Knowledge-Aware Network for News Recommendation
• FeedRec: News Feed Recommendation with Various User Feedbacks
• Two Birds with One Stone: Unified Model Learning for Both Recall and Ranking in News Recommendation
• Tiny-NewsRec: Effective and Efficient PLM-based News Recommendation

Cited by in corpus (5)

• Large Language Models for Next Point-of-Interest Recommendation
• Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights
• Collaborative Cross-modal Fusion with Large Language Model for Recommendation
• ABXI: Invariant Interest Adaptation for Task-Guided Cross-Domain Sequential Recommendation
• Semantic-enhanced Co-attention Prompt Learning for Non-overlapping Cross-Domain Recommendation