English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Text Is All You Need: Learning Language Representations for Sequential Recommendation (arXiv 2305.13731)

Forum topic · 小凯 · 2026-07-05

Summary

"Text Is All You Need: Learning Language Representations for Sequential Recommendation" (arXiv:2305.13731, May 2023) introduces Recformer, a framework that treats sequential recommendation as a language modeling task by representing items purely as text. Instead of relying on item IDs, the model encodes item metadata (title, brand, category, features) as textual descriptions and learns language representations for both items and user behavior sequences. Built on a Longformer-style encoder, Recformer is pretrained with a novel contrastive objective that makes similar items close in the embedding space, and then fine-tuned to predict the next item from a user's interaction history interpreted as a "sentence" of item texts. This design enables strong cold-start performance for new items with no interaction data, since recommendations depend on textual semantics rather than collaborative signals. The authors report that Recformer outperforms competitive ID-based and text-based sequential recommendation baselines on multiple public benchmarks. The paper offers a unified text-centric recipe for recommendation and connects to broader trends in applying language models to search, retrieval, and personalization. Source: https://arxiv.org/abs/2305.13731

Text Is All You Need: Learning Language Representations for Sequential Recommendation (arXiv:2305.13731)

Source: https://arxiv.org/abs/2305.13731 · arXiv, May 2023 Authors: Jiacheng Li, Ming Wang, Jin Li, Jinmiao Fu, Xin Shen, Jingbo Shang, et al. (7 authors in total)

Overview

This paper proposes Recformer, a sequential recommendation framework that uses text as the sole representation of items. Rather than learning large embedding tables for item IDs, the model treats each item as a piece of text (title, brand, category, and attribute keywords) and a user's interaction history as a sequence of such texts — effectively casting sequential recommendation as a language understanding problem.

Key Ideas

  • Items as text: Every item is described by its textual metadata, so no ID embeddings are needed. This makes the approach naturally suited to cold-start scenarios, where new items have no interaction history but do have descriptions.
  • Language model backbone: Recformer builds on a Longformer-style transformer encoder that can handle long concatenated item-text sequences representing a user's behavior history.
  • Text-contrastive pretraining: The model is pretrained with a contrastive learning objective designed to pull semantically and behaviorally similar items close together in the representation space, aligning the language encoder with recommendation needs.
  • Next-item prediction as text selection: At fine-tuning and inference time, the model scores candidate items by their textual fit with the user's history "sentence," selecting the next item accordingly.
  • Reported Results

    The authors evaluate on public sequential recommendation benchmarks and report that Recformer outperforms competitive ID-based and text-based baselines, while transferring well to items unseen during training thanks to its text-based representation. Exact numbers should be verified against the paper's tables.

    Why It Matters

  • Unified recipe: Recommendation inherits the generalization of pretrained language models, reducing the need for task-specific item ID architectures.
  • Cold-start friendly: New and long-tail items can be recommended immediately from metadata alone.
  • Industry relevance: Co-authored by Amazon researchers, the work reflects production interest in language-model-driven personalization.
  • Related Entries

  • 360Brew: A Decoder-only Foundation Model for Personalized Ranking
  • Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers
  • Bridging Language and Items for Retrieval and Recommendation (Mar 2024)
  • Data-efficient Fine-tuning for LLM-based Recommendation, SIGIR 2024
  • DiffKG: Knowledge Graph Diffusion Model for Recommendation, WSDM 2024
  • References

  • Li, J., Wang, M., Li, J., Fu, J., Shen, X., Shang, J., et al. *Text Is All You Need: Learning Language Representations for Sequential Recommendation.* arXiv:2305.13731, May 2023. https://arxiv.org/abs/2305.13731

Tags

#sequential-recommendation#language-models#recformer#cold-start#contrastive-learning#recommender-systems#arxiv#nlp

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208925