深度学习检索框架的前沿探索

郭嘉丰; 范意兴

doi:10.7544/issn1000-1239.2018.20180133

深度学习检索框架的前沿探索

(中国科学院网络数据科学与技术重点实验室(中国科学院计算技术研究所) 北京 100190) (中国科学院计算技术研究所北京 100190) (guojiafeng@ict.ac.cn)

基金项目: 国家自然科学基金优秀青年科学基金项目(61722211) This work was supported by the National Natural Science Foundation of China for Excellent Young Scientists (61722211).

详细信息

中图分类号: TP391
计量
- 文章访问数: 2055
- HTML全文浏览量: 5
- PDF下载量: 976
出版历程
- 发布日期: 2018-08-31

Exploration on Neural Information Retrieval Framework

(CAS Key Laboratory of Network Data Science & Technology(Institute of Computing Technology, Chinese Academy of Sciences), Beijing 100190) (Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190)

摘要

摘要: 经过几十年的发展，信息检索技术获得了长足的进步和广泛的应用，但当前主流的搜索引擎系统距离真正智能的信息获取系统仍然有较大差距.智能信息获取系统能够对网络大数据的内容进行获取、阅读和理解，对关键语义信息实现存储和检索，并能够依据用户的信息需求进行推理、决策和信息生成.实现这样的系统，迫切需要在检索架构和检索模型上形成根本性的改变和理论突破.近年来，围绕智能信息获取的需求，利用深度学习检索框架展开了系统性研究，在数据表征、数据索引以及检索算法等方向上形成了一系列原创成果，在探索全新的深度学习检索架构上不断迈进.
- 信息检索 /
- 深度学习 /
- 数据表征 /
- 相关匹配 /
- 数据索引
Abstract: After decades of research, information retrieval technology has been significantly advanced and widely applied in our daily life. However, there is still a huge gap between modern search engines and true intelligent information accessing systems. In our opinion, an intelligent information accessing system should be able to crawl, read and understand the content of the big Web data, index and search the key semantic information, and reason, decide and generate the right results based on users’ information need. To develop such kind of systems, we need theoretical breakthrough on the search architecture and models. In recent years, to address the intelligent information accessing problem, we have conducted systematical research on neural information retrieval framework. We have achieved a few of original contributions on text representation, data indexing and relevance matching. However, there is still a long way in this direction and we will continue our exploration on neural information retrieval in the future.
- information retrieval /
- deep learning /
- data representation /
- relevance matching /
- data indexing

HTML全文

参考文献(0)

施引文献(12)

期刊类型引用(4)

1.	李光宇. 基于深度神经网络的多模态信息检索. 计算机应用与软件. 2022(01): 219-224+249 . 百度学术
2.	童瀛，周宇，姚焕章，梁剑，薛虎. 深度神经网络的网络高敏感信息预警算法. 西安工程大学学报. 2021(01): 69-74+87 . 百度学术
3.	赵荷，盖玲. 反向梯度优化深度学习的病毒数据对抗方法. 计算机工程与设计. 2020(06): 1575-1580 . 百度学术
4.	牛海波，赵丹群，郭倩影. 基于BERT和引文上下文的文献表征与检索方法研究. 情报理论与实践. 2020(09): 125-131 . 百度学术