Self-supervised Contrastive BERT Fine-tuning For Fusion-based Reviewed-item Retrieval

Abstract

As natural language interfaces enable users to express increasingly complex natural language queries, there is a parallel explosion of user review content that can allow users to better find items such as restaurants, books, or movies that match these expressive queries. While Neural Information Retrieval (IR) methods have provided state-of-the-art results for matching queries to documents, they have not been extended to the task of Reviewed-Item Retrieval (RIR), where query-review scores must be aggregated (or fused) into item-level scores for ranking. In the absence of labeled RIR datasets, we extend Neural IR methodology to RIR by leveraging self-supervised methods for contrastive learning of BERT embeddings for both queries and reviews. Specifically, contrastive learning requires a choice of positive and negative samples, where the unique two-level structure of our item-review data combined with meta-data affords us a rich structure for the selection of these samples. For contrasti

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keypour2023self

Related papers

• Multi-aspect Reviewed-item Retrieval Via LLM Query Decomposition And Aspect Fusion (2024)0.00
• REFINE On Scarce Data: Retrieval Enhancement Through Fine-tuning Via Model Fusion Of Embedding Models (2024)3.58
• Improving Noise Robustness For Spoken Content Retrieval Using Semi-supervised ASR And N-best Transcripts For Bert-based Ranking Models (2023)3.58
• Domain-adaptive And Scalable Dense Retrieval For Content-based Recommendation (2026)0.00
• Unsupervised Dense Information Retrieval With Contrastive Learning (2021)0.00
• Supervised Fine-tuning Or Contrastive Learning? Towards Better Multimodal LLM Reranking (2025)0.00
• Unsupervised Dense Retrieval With Conterfactual Contrastive Learning (2024)0.00
• DS@GT At TREC TOT 2025: Bridging Vague Recollection With Fusion Retrieval And Learned Reranking (2026)0.00