Enhancing Topical Ranking with Preferences from Click-Through Data

被引：0

作者：

Chang, Yi ^{[1
]}

Dong, Anlei ^{[1
]}

Liao, Ciya ^{[1
]}

Zheng, Zhaohui ^{[1
]}

机构：

[1] Yahoo Labs, Sunnyvale, CA 94089 USA

来源：

PROCEEDINGS 32ND ANNUAL INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL | 2009年

关键词：

topical ranking; preference learning; click-through data;

D O I：

10.1145/1571941.1572068

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

To overcome the training data insufficiency problem for dedicated model in topical ranking, this paper proposes to utilize click-through data to improve learning. The efficacy of click-through data is explored under the framework of preference learning. The empirical experiment on a commercial search engine shows that, the model trained with the dedicated labeled data combined with skip-next preferences could beat the baseline model and the generic model in NDCG(5) for 4.9% and 2.4% respectively.

引用

页码：666 / 667

页数：2

共 50 条

[1] Adapting document ranking to users' preferences using click-through data
Zhao, Min
Li, Hang
Ratnaparkhi, Adwait
Hon, Hsiao-Wuen
Wang, Jue
[J]. INFORMATION RETRIEVAL TECHNOLOGY, PROCEEDINGS, 2006, 4182 : 26 - 42
[2] Recommending better queries from click-through data
Dupret, Georges
Mendoza, Marcelo
[J]. STRING PROCESSING AND INFORMATION RETRIEVAL, PROCEEDINGS, 2005, 3772 : 41 - 44
[3] ENHANCING PRODUCT IMAGES FOR CLICK-THROUGH RATE IMPROVEMENT
Chae, Yeongnam
Nakazawa, Mitsuru
Stenger, Bjorn
[J]. 2018 25TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2018, : 1428 - 1432
[4] DECK: Detecting Events from Web Click-through Data
Chen, Ling
Hu, Yiqun
Nejdl, Wolfgang
[J]. ICDM 2008: EIGHTH IEEE INTERNATIONAL CONFERENCE ON DATA MINING, PROCEEDINGS, 2008, : 123 - +
[5] A3CRank: An adaptive ranking method based on connectivity, content and click-through data
Bidoki, Ali Mohammad Zareh
Ghodsnia, Pedram
Yazdani, Nasser
Oroumchian, Farhad
[J]. INFORMATION PROCESSING & MANAGEMENT, 2010, 46 (02) : 159 - 169
[6] Exploiting Click-Through Data for Entity Retrieval
Billerbeck, Bodo
Demartini, Gianluca
Firan, Claudiu S.
Iofciu, Tereza
Krestel, Ralf
[J]. SIGIR 2010: PROCEEDINGS OF THE 33RD ANNUAL INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH DEVELOPMENT IN INFORMATION RETRIEVAL, 2010, : 803 - 804
[7] Usefulness of Click-through data in Expert Search
Macdonald, Craig
White, Ryen W.
[J]. PROCEEDINGS 32ND ANNUAL INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 2009, : 816 - 817
[8] Objectionable Content Filtering by Click-Through Data
Lee, Lung-Hao
Juan, Yen-Cheng
Chen, Hsin-Hsi
Tseng, Yuen-Hsien
[J]. PROCEEDINGS OF THE 22ND ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM'13), 2013, : 1581 - 1584
[9] Improving Click Model by Combining Mouse Movements with Click-Through Data
Chen, Xia
Min, Huaqing
[J]. PROCEEDINGS OF 2015 6TH IEEE INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING AND SERVICE SCIENCE, 2015, : 183 - 187
[10] Identifying and Classifying Named Entities from Click-through Data Effectively
Jiang, Xuan
Liu, Hongyan
Cheng, Hong
He, Jun
Du, Xiaoyong
[J]. ELECTRONIC-BUSINESS INTELLIGENCE: FOR CORPORATE COMPETITIVE ADVANTAGES IN THE AGE OF EMERGING TECHNOLOGIES & GLOBALIZATION, 2010, 14 : 476 - +

← 1 2 3 4 5 →