Skip to content
TheChatArchiveThe Chat Archive
gpt-4o-search-preview· OpenAIHugging Face LMArena Search Arena 24K

What are the best research papers on improving search semantic retrieval in e-commerce

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with Perplexitysonar’s answer.
  1. User

    What are the best research papers on improving search semantic retrieval in e-commerce

  2. Assistant

    Improving semantic retrieval in e-commerce is a critical area of research, aiming to enhance the relevance and personalization of search results. Here are some notable research papers that have contributed significantly to this field:

    1. "From Semantic Retrieval to Pairwise Ranking: Applying Deep Learning in E-commerce Search" by Rui Li et al. (2021): This paper introduces deep learning models into two key stages of product search: semantic retrieval and pairwise ranking. The proposed system retrieves semantically relevant items within milliseconds and learns subtle user preferences, leading to significant improvements over traditional search systems[1].

    2. "Towards Personalized and Semantic Retrieval: An End-to-End Solution for E-commerce Search via Embedding Learning" by Han Zhang et al. (2020): The authors present DPSR (Deep Personalized and Semantic Retrieval), an approach that addresses the challenges of retrieving semantically relevant and personalized items. The system has been successfully deployed in JD.com's search production, improving user experience and conversion rates[2].

    3. "Cluster Language Model for Improved E-Commerce Retrieval and Ranking: Leveraging Query Similarity and Fine-Tuning for Personalized Results" by Duleep Rathgamage Don et al. (2024): This paper proposes a method to enhance product search accuracy by utilizing a cluster language model. By generating semantically similar query clusters and fine-tuning language models on these clusters, the approach captures nuances of various query types, resulting in more accurate and personalized retrieval results[3].

    4. "Improving Relevance Quality in Product Search using High-Precision Query-Product Semantic Similarity" by Alireza Bagheri Garakani et al. (2022): The authors leverage a high-precision cross-encoder BERT model to measure semantic similarity between customer queries and products. This strategy enhances relevance quality in product search, demonstrating effectiveness in large e-commerce settings[4].

    5. "Semantic Equivalence of e-Commerce Queries" by Aritra Mandal et al. (2023): This paper introduces a framework to recognize and leverage query equivalence, addressing the challenge of search query variation. By mapping queries to vector representations and identifying nearest neighbor queries with similar intent, the approach improves user experiences and business outcomes in e-commerce search[5].

    6. "Enhancing e-commerce product search through reinforcement learning-powered query reformulation" by Sanjay Agrawal et al. (2023): The authors propose RLQR (Reinforcement Learning for Query Reformulations), a method that generates high-quality, diverse reformulations to maximize product coverage. This approach demonstrates a significant increase in product coverage compared to standard generative models[6].

    7. "Semantic-enhanced Modality-asymmetric Retrieval for Online E-commerce Search" by authors (2023): This paper addresses the multimodal retrieval problem by leveraging visual information of items to enrich representations and improve retrieval performance. The proposed SMAR model tackles modality fusion and alignment in asymmetric scenarios, showing significant improvements in retrieval accuracy[7].

    These papers offer valuable insights and methodologies for enhancing semantic retrieval in e-commerce, focusing on deep learning applications, personalized retrieval, query reformulation, and multimodal information integration.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.