Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2405.11441 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911992309088256 |
|---|---|
| author | Zhang, Chiyu Sun, Yifei Wu, Minghao Chen, Jun Lei, Jie Abdul-Mageed, Muhammad Jin, Rong Liu, Angli Zhu, Ji Park, Sem Yao, Ning Long, Bo |
| author_facet | Zhang, Chiyu Sun, Yifei Wu, Minghao Chen, Jun Lei, Jie Abdul-Mageed, Muhammad Jin, Rong Liu, Angli Zhu, Ji Park, Sem Yao, Ning Long, Bo |
| contents | Content-based recommendation systems play a crucial role in delivering personalized content to users in the digital world. In this work, we introduce EmbSum, a novel framework that enables offline pre-computations of users and candidate items while capturing the interactions within the user engagement history. By utilizing the pretrained encoder-decoder model and poly-attention layers, EmbSum derives User Poly-Embedding (UPE) and Content Poly-Embedding (CPE) to calculate relevance scores between users and candidate items. EmbSum actively learns the long user engagement histories by generating user-interest summary with supervision from large language model (LLM). The effectiveness of EmbSum is validated on two datasets from different domains, surpassing state-of-the-art (SoTA) methods with higher accuracy and fewer parameters. Additionally, the model's ability to generate summaries of user interests serves as a valuable by-product, enhancing its usefulness for personalized content recommendations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_11441 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EmbSum: Leveraging the Summarization Capabilities of Large Language Models for Content-Based Recommendations Zhang, Chiyu Sun, Yifei Wu, Minghao Chen, Jun Lei, Jie Abdul-Mageed, Muhammad Jin, Rong Liu, Angli Zhu, Ji Park, Sem Yao, Ning Long, Bo Information Retrieval Computation and Language Content-based recommendation systems play a crucial role in delivering personalized content to users in the digital world. In this work, we introduce EmbSum, a novel framework that enables offline pre-computations of users and candidate items while capturing the interactions within the user engagement history. By utilizing the pretrained encoder-decoder model and poly-attention layers, EmbSum derives User Poly-Embedding (UPE) and Content Poly-Embedding (CPE) to calculate relevance scores between users and candidate items. EmbSum actively learns the long user engagement histories by generating user-interest summary with supervision from large language model (LLM). The effectiveness of EmbSum is validated on two datasets from different domains, surpassing state-of-the-art (SoTA) methods with higher accuracy and fewer parameters. Additionally, the model's ability to generate summaries of user interests serves as a valuable by-product, enhancing its usefulness for personalized content recommendations. |
| title | EmbSum: Leveraging the Summarization Capabilities of Large Language Models for Content-Based Recommendations |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2405.11441 |