In book search, relevant book information should be returned in response to a query. Books contain complex, multi-faceted information such as metadata, outlines, and main text, where the outline provides hierarchical information between chapters and sections. Generative retrieval (GR) is a new retrieval paradigm that consolidates corpus information into a single model to generate identifiers of documents that are relevant to a given query. How can GR be applied to book search? Directly applying GR to book search is a challenge due to the unique characteristics of book search: The model needs to retain the complex, multi-faceted information of the book, which increases the demand for labeled data. Splitting book information and treating it as a collection of separate segments for learning might result in a loss of hierarchical information. We propose an effective Generative retrieval framework for Book Search (GBS) that features two main components: data augmentation and outline-oriented book encoding. For data augmentation, GBS constructs multiple query-book pairs for training; it constructs multiple book identifiers based on the outline, various forms of book contents, and simulates real book retrieval scenarios with varied pseudo-queries. This includes coverage-promoting book identifier augmentation, allowing the model to learn to index effectively, and diversity-enhanced query augmentation, allowing the model to learn to retrieve effectively. Outline-oriented book encoding improves length extrapolation through bi-level positional encoding and retentive attention mechanisms to maintain context over long sequences. Experiments on a proprietary Baidu dataset demonstrate that GBS outperforms strong baselines, achieving a 9.8\% improvement in terms of MRR@20, over the state-of-the-art RIPOR method...
Efficient Media Retrieval from Non-Cooperative Queries
University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);eBay Research Labs(eBay研究实验室)
文本在人工世界中无处不在,当涉及到书名和作者姓名时,文本很容易获得。使用来自Stanford Mobile Visual Search数据集的书籍封面集的图像以及来自openlibrary.org的其他书籍封面和元数据,我们构建了一个大规模的书籍封面检索数据集,每个数据集包含10万个干扰项封面以及标题和作者字符串。由于我们的查询图像是不好的条件,干净的文本提取,我们提出了一种方法,用于提取匹配的噪声和错误的OCR读数,并匹配它对干净的作者和书名字符串在一个标准的文档查找问题设置。最后,我们演示了如何使用这种文本匹配作为一个功能,结合流行的检索功能,如VLAD使用一个简单的学习设置,以实现检索精度的显着改善,无论是VLAD或单独的文本。
A Generative Framework for Personalized Sticker Retrieval
State Key Laboratory of AI Safety, Institute of Computing Technology, CAS(中国科学院计算技术研究所人工智能安全国家重点实验室);University of Chinese Academy of Sciences(中国科学院大学);WeChat Search Application Department, Tencent Inc.(腾讯公司微信搜索应用部)
Does Generative Retrieval Overcome the Limitations of Dense Retrieval?
State Key Laboratory of AI Safety, Institute of Computing Technology, CAS(中国科学院计算技术研究所人工智能安全重点实验室);University of Chinese Academy of Sciences(中国科学院大学);University of Amsterdam(阿姆斯特丹大学)
本文从学习目标与表示能力两方面对比生成式检索与稠密检索,揭示 GR 在语料和模型扩展下的理论优势,并通过实验验证,同时指出其实践差距与未来研究方向。
Continual Learning for Generative Retrieval over Dynamic Corpora
CAS Key Lab of Network Data Science and Technology, ICT, CAS(中国科学院网络数据科学与技术重点实验室);University of Chinese Academy of Sciences(中国科学院大学);University of Amsterdam(阿姆斯特丹大学)
Evaluating Generative Ad Hoc Information Retrieval
Leipzig University(莱比锡大学);The University of Queensland(昆士兰大学);Bauhaus-Universität Weimar(魏玛包豪斯大学);Friedrich-Schiller-Universität Jena(弗里德里希·席勒大学耶拿分校);University of Kassel(卡塞尔大学)
Exploring Training and Inference Scaling Laws in Generative Retrieval
National University of Singapore(新加坡国立大学);The Hong Kong Polytechnic University(香港理工大学);University of Science and Technology of China(中国科学技术大学);Nanyang Technological University(南洋理工大学)