Text Is All You Need: Learning Language Representations for Sequential Recommendation

TL;DR

This paper introduces Recformer, a novel language-based framework for sequential recommendation that models user preferences and items as language representations, improving cold-start and transfer learning performance.

Contribution

Recformer is the first to formulate items as sentences and apply language modeling techniques to sequential recommendation, enhancing generalization to new items and datasets.

Findings

Effective in cold-start scenarios

Outperforms baselines on six datasets

Improves recommendation accuracy with language representations

Abstract

Sequential recommendation aims to model dynamic user behavior from historical interactions. Existing methods rely on either explicit item IDs or general textual features for sequence modeling to understand user preferences. While promising, these approaches still struggle to model cold-start items or transfer knowledge to new datasets. In this paper, we propose to model user preferences and item features as language representations that can be generalized to new items and datasets. To this end, we present a novel framework, named Recformer, which effectively learns language representations for sequential recommendation. Specifically, we propose to formulate an item as a "sentence" (word sequence) by flattening item key-value attributes described by text so that an item sequence for a user becomes a sequence of sentences. For recommendation, Recformer is trained to understand the "sentence" sequence and retrieve the next "sentence". To encode item sequences, we design a bi-directional Transformer similar to the model Longformer but with different embedding layers for sequential recommendation. For effective representation learning, we propose novel pretraining and finetuning methods which combine language understanding and recommendation tasks. Therefore, Recformer can effectively recommend the next item based on language representations. Extensive experiments conducted on six datasets demonstrate the effectiveness of Recformer for sequential recommendation, especially in low-resource and cold-start settings.