相关实验视频

Updated: May 1, 2026

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

为生成性检索进行渐进式分类:一种自我监督的方法来实现高质量的DocID生成

Shunyu Yao¹, Jie Hu¹, Zhiyuan Zhang²

¹China Telecom Research Institute, Beijing, 102209, China.

Neural networks : the official journal of the International Neural Network Society

|June 14, 2025

概括

这项研究引入了自我监督的渐进式分离化 (SPD),通过创建更好的文档标识符 (DocID) 来改善生成检索. SPD提高了生成检索性能,克服了当前无监督方法的局限性.

科学领域:

信息检索信息检索
机器学习机器学习
自然语言处理自然语言处理.

背景情况:

生成式检索利用大型语言模型作为文档记忆和检索的可区分索引.
传统方法将文档和查询单独编码,从而限制了性能.
目前用于大规模检索的文档标识符 (DocID) 的方法通常由于无监督的分类而遭受信息扭曲.

研究的目的:

提出一种新的框架,即自主监督的渐进式分离化 (SPD),用于生成高质量的,以搜索为导向的文档标识符 (DocID).
解决无监督 DocID 生产中信息扭曲的问题.
提高生成检索系统的性能.

主要方法:

通过自主监督学习,SPD将文档信息提炼成多视角的连续表示.
一个渐进式离散算法将连续表示转换为近似向量和离散的DocID.
自主监督模型,近似向量和DocID被集成到查询侧的培训管道中.

主要成果:

SPD成功地生成了高质量的,以搜索为导向的DocID.
拟议的框架在生成检索任务中实现了最先进的性能.
在流行基准上的实验验验证了SPD的有效性.

结论:

自主监督的渐进式分密化 (SPD) 提供了一个强大的解决方案,用于创建有效的文档标识符,用于生成检索.
SPD 减轻了无监督 DocID 生成所固有的信息扭曲.
该框架显著提升了生成检索系统的能力.

关键词:

具有生成性的检索.语言模型语言模型神经网络的神经网络自主监督的渐进式分类.

更多相关视频

Using Generative Art to Convey Past and Future Climate Transitions

Using Generative Art to Convey Past and Future Climate Transitions

Published on: March 31, 2023

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

相关概念视频

Methods of Classification and Identification

Methods of Classification and Identification

Bacterial identification relies on a diverse array of techniques to classify and understand microorganisms, each tailored to uncover specific characteristics. Traditional morphological approaches, while still valuable, are limited for closely related or structurally simple organisms. Modern methods integrate biochemical, serological, genetic, and advanced molecular tools to achieve greater accuracy.Morphological and Biochemical TechniquesMorphological characteristics, such as cell shape and...

Automated Microbial Diagnostics

Automated Microbial Diagnostics

Automated diagnostic analyzers have transformed clinical microbiology by providing rapid and reliable methods for pathogen identification and antibiotic susceptibility testing. Among these systems, the Vitek 2 is widely used because it automates the traditionally labor-intensive processes of microbial identification (ID) and antibiotic susceptibility testing (AST), delivering standardized and timely results that are essential for effective patient care.Microbial Identification with ID CardsThe...