[1]田 媛,郝文宁,陈 刚,等.用于信息检索的句子级深度关联匹配模型[J].计算机技术与发展,2022,32(06):9-14.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 002]
　TIAN Yuan,HAO Wen-ning,CHEN Gang,et al.Sentence Level Deep Relevance Matching Model for Information Retrieval[J].,2022,32(06):9-14.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 002]
点击复制

用于信息检索的句子级深度关联匹配模型()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年06期
页码:
9-14
栏目:
人工智能
出版日期:
2022-06-10

文章信息/Info

Title:
Sentence Level Deep Relevance Matching Model for Information Retrieval
文章编号:
1673-629X(2022)06-0009-06
作者:
田 媛; 郝文宁; 陈 刚; 靳大尉; 邹 傲
陆军工程大学 指挥控制工程学院,江苏 南京 210001
Author(s):
TIAN Yuan; HAO Wen-ning; CHEN Gang; JIN Da-wei; ZOU Ao
School of Command & Control Engineering,Army Engineering University of PLA,Nanjing 210001,China
关键词:
信息检索; 句子级; 深度关联匹配; 前馈匹配网络; 门控网络
Keywords:
information retrieval; sentence level; deep relevance matching; feed-forward neural network; gating network
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 06. 002
摘要:
信息检索( information retrieval,IR)一直是自然语言处理( natural language processing,NLP) 中的研究热点,随着深度学习在 NLP 任务中的不断发展,研究者尝试使用神经信息检索模型成功捕获了查询与待检索文档之间的关联匹配信息,但是现有的工作通常是以词为单位做关联匹配,没有充分考虑词序以及词的上下文信息,无法解决语句中可能存在的一词多义问题。 为了获取查询与待检索文档之间的深层交互信息,对句子级深度关联匹配模型进行了研究,以相对于词来说语义更加完整的句子为单位对查询和待检索文档进行切分,对每一个查询句,计算与待检索文档中每个句子的相似度得分并按照相似度等级映射成固定长度的局部关联匹配直方图,使用前馈匹配网络学习层次匹配信息为每个查询句计算一个匹配分数,门控网络聚合全部查询句的匹配分数以获取最终查询-文档对的相似度得分。 在 Med 数据集上的实验结果表明,句子级深度关联匹配模型较传统的检索模型以及一些无监督句子级检索模型能有效提高检索性能。
Abstract:
Information retrieval has always been a hot issue in natural language processing. In recent years, deep learning has led to exciting breakthroughs in NLP tasks,with its continuous development,researchers have tried to use neural information retrieval model to successfully capture the relevance matching information between queries and documents to be retrieved. However, the existing work usually carries out relevance matching at the word level, without giving full consideration to word order and the semantic relations between words. In order to obtain the deep interaction information between query and documents to be retrieved, a deep relevance matching model at sentence level is studied,the query and the documents to be retrieved are segmented by sentences that are semantically more complete than words,for each query sentence,mapping the variable-length local interaction into a fixed-length matching histogram according to the level of the similarity. Then a feed-forward neural matching network and a term gating network are used to obtain the final similarity score between the query and the document pairs. Experimental results on the MED dataset show that the proposed model outperforms some traditional retrieval model as well as unupervised sentence level models.

相似文献/References:

[1]汪小珍 李龙澍.基于模糊集的信息检索方法[J].计算机技术与发展,2010,(02):37.
　WANG Xiao-zhen,LI Long-shu.An Information Retrieval Scheme Based on Fuzzy Set[J].,2010,(06):37.
[2]杜光芹 张化祥 赵瑞东.主题Web挖掘研究[J].计算机技术与发展,2008,(02):94.
　DU Guang-qin,ZHANG Hua-xiang,ZHAO Rui-dong.State of Topic Web Mining[J].,2008,(06):94.
[3]李桂华 汪学明.语义信息检索框架设计及其算法研究[J].计算机技术与发展,2010,(08):41.
　LI Gui-hua,WANG Xue-ming.Research of Framework and Algorithm of Semantic Information Retrieval[J].,2010,(06):41.
[4]周瑛 张铃.模糊集方法在检索评价系统中的应用[J].计算机技术与发展,2007,(01):111.
　ZHOU Ying,ZHANG Ling.Application of Fuzzy Measure in Information Retrieval Evaluation[J].,2007,(06):111.
[5]张丽坤 蒋波.基于本体的语义Web研究[J].计算机技术与发展,2007,(06):116.
　ZHANG Li-kun,JIANG Bo.Research on Ontology- Based Semantic Web[J].,2007,(06):116.
[6]杨文忠 章兢.用信息-摘要算法提高Web信息检索效率的研究[J].计算机技术与发展,2006,(06):222.
　YANG Wen-zhong,ZHANG Jing.Using Message- Digest Algorithm for improving Efficiency of Web information Searching[J].,2006,(06):222.
[7]王预.数字图书馆信息检索技术及其应用[J].计算机技术与发展,2006,(10):226.
　WANG Yu.Information Retrieval Technique of Digital Library and Its Application[J].,2006,(06):226.
[8]周锦程 王丹 余泉 张维.基于Lucene的全文检索系统的研究与实现[J].计算机技术与发展,2011,(03):67.
　ZHOU Jin-cheng,WANG Dan,YU Quan,et al.Research and Implementation of Full-Text Retrieval Engine Based on Lucene[J].,2011,(06):67.
[9]何拥军 龚发根.基于用户辅助估计的相关网页搜索聚类[J].计算机技术与发展,2011,(07):112.
　HE Yong-jun,GONG Fa-gen.Clustering of Related Pages Based User-Assisted Estimation[J].,2011,(06):112.
[10]黄名选 冯平 谢统义.基于语词抽取与负关联规则挖掘的信息检索[J].计算机技术与发展,2012,(05):157.
　HUANG Ming-xuan,FENG Ping,XIE Tong-yi.Information Retrieval Based on Terms Extraction and Negative Association Rules Mining[J].,2012,(06):157.

更新日期/Last Update: 2022-06-10