Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval

Author:

Xiao Shitao1,Liu Zheng2,Han Weihao3,Zhang Jianjin3,Shao Yingxia1,Lian Defu4,Li Chaozhuo2,Sun Hao3,Deng Denvy3,Zhang Liangjie3,Zhang Qi3,Xie Xing2

Affiliation:

1. Beijing University of Posts and Telecommunications, China

2. Microsoft Research Asia, China

3. Microsoft Search Technology Center Asia, China

4. University of Science and Technology of China, China

Funder

National Natural Science Foundation of China

Publisher

ACM

Reference44 articles.

1. Nilesh Padhariya Anirban Mondal , Ayaan Kakkar and Mukesh Mohania . 2021 . Efficient Indexing of Top-k Entities in Systems of Engagement with Extensions for Geo-tagged Entities. Data Science and Engineering( 2021). Nilesh Padhariya Anirban Mondal, Ayaan Kakkar and Mukesh Mohania. 2021. Efficient Indexing of Top-k Entities in Systems of Engagement with Extensions for Geo-tagged Entities. Data Science and Engineering(2021).

2. Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors

3. Shape indexing using approximate nearest-neighbour search in high-dimensional spaces

4. Yoshua Bengio Nicholas Léonard and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432(2013). Yoshua Bengio Nicholas Léonard and Aaron Courville. 2013. Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432(2013).

5. Wei-Cheng Chang Felix X Yu Yin-Wen Chang Yiming Yang and Sanjiv Kumar. 2020. Pre-training tasks for embedding-based large-scale retrieval. arXiv preprint arXiv:2002.03932(2020). Wei-Cheng Chang Felix X Yu Yin-Wen Chang Yiming Yang and Sanjiv Kumar. 2020. Pre-training tasks for embedding-based large-scale retrieval. arXiv preprint arXiv:2002.03932(2020).

Cited by 7 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. C-Pack: Packed Resources For General Chinese Embeddings;Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval;2024-07-10

2. FIT-RAG: Black-Box RAG with Factual Information and Token Reduction;ACM Transactions on Information Systems;2024-07-09

3. NoteLLM: A Retrievable Large Language Model for Note Recommendation;Companion Proceedings of the ACM Web Conference 2024;2024-05-13

4. RIF-Proto: A Few-Shot Relation Extraction for Prototype Networks Based on Relational Information Features;2024 5th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT);2024-03-29

5. An efficient long-text semantic retrieval approach via utilizing presentation learning on short-text;Complex & Intelligent Systems;2023-08-14

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3