Explore Entity Embedding Effectiveness in Entity Retrieval.
作者： Zhenghao Liu , Chenyan Xiong , Maosong Sun , Zhiyuan Liu
DOI: 10.1007/978-3-030-32381-3_9
关键词: Knowledge graph 、 Learning to rank 、 Structural representation 、 Semantic information 、 Embedding 、 Information retrieval 、 Feature (linguistics) 、 Representation (systemics) 、 Distributed representation 、 Computer science
摘要: This paper explores entity embedding effectiveness in ad-hoc retrieval, which introduces distributed representation of entities into retrieval. The knowledge graph contains lots and models semantic relations with the well-formed structural representation. Entity learns information from represents a low-dimensional representation, provides an opportunity to establish interactions between query related candidate for Our experiments demonstrate based model, achieves more than 5% improvement previous state-of-the-art learning rank retrieval model. further analysis reveals that match feature effective, especially scenario needs understanding.
springer.com
arxiv.org
sci-hub.st 参考文章(18)
Jinyoung Kim, Xiaobing Xue, W. Bruce Croft, A Probabilistic Retrieval Model for Semistructured Data Lecture Notes in Computer Science. pp. 228- 239 ,(2009) , 10.1007/978-3-642-00958-7_22
Gianluca Demartini, Tereza Iofciu, Arjen P. de Vries, Overview of the INEX 2009 entity ranking track INEX'09 Proceedings of the Focused retrieval and evaluation, and 8th international conference on Initiative for the evaluation of XML retrieval. ,vol. 6203, pp. 254- 264 ,(2009) , 10.1007/978-3-642-14556-8_26
Jeffrey Pound, Peter Mika, Hugo Zaragoza, Ad-hoc object retrieval in the web of data the web conference. pp. 771- 780 ,(2010) , 10.1145/1772690.1772769
Krisztian Balog, Robert Neumayer, A test collection for entity search in DBpedia international acm sigir conference on research and development in information retrieval. pp. 737- 740 ,(2013) , 10.1145/2484028.2484165
Nikita Zhiltsov, Alexander Kotov, Fedor Nikolaev, Fielded Sequential Dependence Model for Ad-Hoc Entity Retrieval in the Web of Data international acm sigir conference on research and development in information retrieval. pp. 253- 262 ,(2015) , 10.1145/2766462.2767756
Donald Metzler, W. Bruce Croft, A Markov random field model for term dependencies international acm sigir conference on research and development in information retrieval. pp. 472- 479 ,(2005) , 10.1145/1076034.1076115
Paul Ogilvie, Jamie Callan, Combining document representations for known-item search international acm sigir conference on research and development in information retrieval. pp. 143- 150 ,(2003) , 10.1145/860435.860463
Stephen Robertson, Hugo Zaragoza, Michael Taylor, Simple BM25 extension to multiple weighted fields conference on information and knowledge management. pp. 42- 49 ,(2004) , 10.1145/1031171.1031181
Krisztian Balog, Marc Bron, Maarten De Rijke, Query modeling for entity search based on terms, categories, and examples ACM Transactions on Information Systems. ,vol. 29, pp. 1- 31 ,(2011) , 10.1145/2037661.2037667
Michael Bendersky, Donald Metzler, W. Bruce Croft, Learning concept importance using a weighted dependence model web search and data mining. pp. 31- 40 ,(2010) , 10.1145/1718487.1718492