arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.05441cs.IRcs.AI
收藏

语言表示可以成为推荐系统所需:发现与潜力

Language Representations Can be What Recommenders Need: Findings and Potentials

National University of Singapore(新加坡国立大学);University of Science and Technology of China(中国科学技术大学)

Leheng Sheng, An Zhang, Yi Zhang, Yuxin Chen, Xiang Wang, Tat-Seng Chua

AI总结:

本研究重新审视语言模型与推荐系统表示空间的关系,发现从先进语言表示线性映射的项目表示可提升推荐性能,并构建了仅基于语言表示的简单协同过滤模型,超越基于ID的模型,揭示了语言建模与行为建模的潜在联系。

摘要:

近期研究经验性地表明,语言模型(LMs)编码了超越单纯语义的丰富世界知识,吸引了各个领域的广泛关注。然而,在推荐领域,尚不确定语言模型是否隐式编码了用户偏好信息。与主流理解(即由于语言和行为建模目标之间存在巨大差距,语言模型和传统推荐器学习两个不同的表示空间)相反,本研究重新审视了这种理解,并探索直接从语言表示空间中提取推荐空间。令人惊讶的是,我们的发现表明,当从先进语言模型表示线性映射项目表示时,能产生优越的推荐性能。这一结果表明,先进语言表示空间与有效的推荐项目表示空间之间可能存在同构性,意味着协同信号可能被隐式编码在语言模型中。受这些发现的启发,我们探索了纯粹基于语言表示设计先进协同过滤(CF)模型的可能性,而无需基于ID的嵌入。具体来说,我们整合了几个关键组件,构建了一个简单而有效的模型,以项目标题作为输入。实证结果表明,这样一个简单的模型可以超越领先的基于ID的CF模型,这为使用语言表示实现更好的推荐提供了启示。此外,我们系统分析了这一简单模型,并发现了使用先进语言表示的几个关键特征:项目表示的良好初始化、零样本推荐能力以及对用户意图的感知。我们的发现强调了语言建模和行为建模之间的联系,这可以激励自然语言处理和推荐系统社区。

英文摘要:

Recent studies empirically indicate that language models (LMs) encode rich world knowledge beyond mere semantics, attracting significant attention across various fields. However, in the recommendation domain, it remains uncertain whether LMs implicitly encode user preference information. Contrary to prevailing understanding that LMs and traditional recommenders learn two distinct representation spaces due to the huge gap in language and behavior modeling objectives, this work re-examines such understanding and explores extracting a recommendation space directly from the language representation space. Surprisingly, our findings demonstrate that item representations, when linearly mapped from advanced LM representations, yield superior recommendation performance. This outcome suggests the possible homomorphism between the advanced language representation space and an effective item representation space for recommendation, implying that collaborative signals may be implicitly encoded within LMs. Motivated by these findings, we explore the possibility of designing advanced collaborative filtering (CF) models purely based on language representations without ID-based embeddings. To be specific, we incorporate several crucial components to build a simple yet effective model, with item titles as the input. Empirical results show that such a simple model can outperform leading ID-based CF models, which sheds light on using language representations for better recommendation. Moreover, we systematically analyze this simple model and find several key features for using advanced language representations: a good initialization for item representations, zero-shot recommendation abilities, and being aware of user intention. Our findings highlight the connection between language modeling and behavior modeling, which can inspire both natural language processing and recommender system communities.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑