基于分布式表示语义组合的查询子主题挖掘

宋巍; 刘影; 刘丽珍; 王函石

doi:10.1631/FITEE.1601476

Your Location：

Home >

Browse articles >

基于分布式表示语义组合的查询子主题挖掘

常规文章 | Updated：2022-05-19

- 基于分布式表示语义组合的查询子主题挖掘
- Semantic composition of distributed representations for query subtopic mining
- 信息与电子工程前沿（英文） 2018年19卷第11期页码：1409-1419
- Affiliations：
  
  Information and Engineering College, Capital Normal University, Beijing 100048, China
- Author bio：
  
  Li-zhen LIU, E-mail: liz_liu7480@cnu.edu.cn
- Funds：
  
  Project supported by the National Natural Science Foundation of China (Nos. 61876113 and 61402304), the Beijing Educational Committee Science and Technology Development Plan of China (No. KM201610028015), and the Beijing Advanced Innovation Center for Imaging Technology of China
- DOI：10.1631/FITEE.1601476
  中图分类号： TP391.3
- 收稿：2016-08-15，
  
  修回：2017-11-12，
  
  纸质出版：2018-11
- Accepted：
Scan QR Code
宋巍, 刘影, 刘丽珍, 等. 基于分布式表示语义组合的查询子主题挖掘[J]. 信息与电子工程前沿（英文）, 2018,19(11):1409-1419.

Wei SONG, Ying LIU, Li-zhen LIU, et al. Semantic composition of distributed representations for query subtopic mining[J]. Frontiers of Information Technology & Electronic Engineering, 2018, 19(11): 1409-1419.
宋巍, 刘影, 刘丽珍, 等. 基于分布式表示语义组合的查询子主题挖掘[J]. 信息与电子工程前沿（英文）, 2018,19(11):1409-1419. DOI： 10.1631/FITEE.1601476.

Wei SONG, Ying LIU, Li-zhen LIU, et al. Semantic composition of distributed representations for query subtopic mining[J]. Frontiers of Information Technology & Electronic Engineering, 2018, 19(11): 1409-1419. DOI： 10.1631/FITEE.1601476.

摘要

推断查询意图对于信息检索具有重要意义。查询子主题挖掘旨在找到可能的子主题，用于表示给定查询的潜在意图。由于查询较短，子主题挖掘具有挑战性。学习词或句子分布式表示推动和影响了很多领域的发展。然而，没有清晰的结论表明该分布式表示是否有助于应对查询子主题挖掘面临的挑战。提出并比较利用分布式表示的语义组合进行查询子主题挖掘。采用两种分布式表示策略：能学习任意长度文本分布式表示的段落向量（paragraph vector）以及词向量的语义组合。探索了语义组合策略和数据类型对查询表示的影响。在国家信息学研究所信息获取研究试验平台和社区（National Institute of InformaticsTestbeds and Community for Information Access Research，NTCIR）提供的公开数据集上的实验结果表明，与传统语义表示相比，分布式语义表示能获得更优查询子主题挖掘性能。文中做了更多深入探讨。

Abstract

Inferring query intent is significant in information retrieval tasks. Query subtopic mining aims to find possible subtopics for a given query to represent potential intents. Subtopic mining is challenging due to the nature of short queries. Learning distributed representations or sequences of words has been developed recently and quickly

making great impacts on many fields. It is still not clear whether distributed representations are effective in alleviating the challenges of query subtopic mining. In this paper

we exploit and compare the main semantic composition of distributed representations for query subtopic mining. Specifically

we focus on two types of distributed representations: paragraph vector which represents word sequences with an arbitrary length directly

and word vector composition. We thoroughly investigate the impacts of semantic composition strategies and the types of data for learning distributed representations. Experiments were conducted on a public dataset offered by the National Institute of Informatics Testbeds and Community for Information Access Research. The empirical results show that distributed semantic representations can achieve outstanding performance for query subtopic mining

compared with traditional semantic representations. More insights are reported as well.

关键词

Keywords

references

I Anagnostopoulos , , , G Razis , , , P Mylonas , , , 等 . . Semantic query suggestion using Twitter entities . . Neurocomputing , , 2015 . . 163 137 - - 150 . . DOI: 10.1016/j.neucom.2014.12.090 http://doi.org/10.1016/j.neucom.2014.12.090 . .

R Baeza-Yates , , , C Hurtado , , , M Mendoza . . Query recommendation using query logs in search engines . . LNCS , , 2005 . . 3268 588 - - 596 . . DOI: 10.1007/978-3-540-30192-9_58 http://doi.org/10.1007/978-3-540-30192-9_58 . .

M Baroni , , , G Dinu , , , G Kruszewski . . Don't count, predict! A systematic comparison of context-counting vs. contextpredicting semantic vectors . . Proc 52 nd Annual Meeting of the Association for Computational Linguistics , , 2014 . . p.238 - - 247 . . DOI: 10.3115/v1/P14-1023 http://doi.org/10.3115/v1/P14-1023 . .

D Beeferman , , , A Berger . . Agglomerative clustering of a search engine query log . . Proc 6 th ACM SIGKDD Int Conf on Knowledge Discovery and Data Mining , , 2000 . . p.407 - - 416 . . DOI: 10.1145/347090.347176 http://doi.org/10.1145/347090.347176 . .

Y Bengio , , , R Ducharme , , , P Vincent , , , 等 . . A neural probabilistic language model . . J Mach Learn Res , , 2003 . . 3 1137 - - 1155 . . . .

CLA Clarke , , , N Craswell , , , I Soboroff . . Overview of the TREC 2009 web track . . 18 th Text Retrieval Conf , , 2009 . . p.1 - - 9 . . . .

R Collobert , , , J Weston . . A unified architecture for natural language processing: deep neural networks with multitask learning . . Proc 25 th Int Conf on Machine Learning , , 2008 . . p.160 - - 167 . . DOI: 10.1145/1390156.1390177 http://doi.org/10.1145/1390156.1390177 . .

A Damien , , , M Zhang , , , Y Liu , , , 等 . . Improve web search diversification with intent subtopic mining . . CCIS , , 2013 . . 400 322 - - 333 . . DOI: 10.1007/978-3-642-41644-6_30 http://doi.org/10.1007/978-3-642-41644-6_30 . .

V Dang , , , X Xue , , , WB Croft . . Inferring query aspects from reformulations using clustering . . Proc 20 th ACM Int Conf on Information and Knowledge Management , , 2011 . . p.2117 - - 2120 . . DOI: 10.1145/2063576.2063904 http://doi.org/10.1145/2063576.2063904 . .

E Grefenstette , , , G Dinu , , , YZ Zhang , , , 等 . . Multi-step regression learning for compositional distributional semantics , , 2013 . . https://arxiv.org/abs/1301.6939 https://arxiv.org/abs/1301.6939 , , . .

J Hu , , , G Wang , , , F Lochovsky , , , 等 . . Understanding user's query intent with Wikipedia . . Proc 18 th Int Conf on World Wide Web , , 2009 . . p.471 - - 480 . . DOI: 10.1145/1526709.1526773 http://doi.org/10.1145/1526709.1526773 . .

Y Hu , , , Y Qian , , , H Li , , , 等 . . Mining query subtopics from search log data . . Proc 35 th Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 2012 . . p.305 - - 314 . . DOI: 10.1145/2348283.2348327 http://doi.org/10.1145/2348283.2348327 . .

X Jiang , , , X Han , , , L Sun . . ISCAS at subtopic mining task in NTCIR9 . . Proc NTCIR-9 Workshop Meeting , , 2011 . . p.168 - - 171 . . . .

H Joho , , , K Kishida . . Overview of NTCIR-11 . . Proc 11 th NTCIR Conf , , 2014 . . p.1 - - 7 . . . .

R Jones , , , KL Klinkner . . Beyond the session timeout: automatic hierarchical segmentation of search topics in query logs . . Proc 17 th ACM Conf on Information and Knowledge Management , , 2008 . . p.699 - - 708 . . DOI: 10.1145/1458082.1458176 http://doi.org/10.1145/1458082.1458176 . .

S Karunasekera , , , A Harwood , , , S Samarawickrama , , , 等 . . Topic-specific post identification in microblog streams . . IEEE Int Conf on Big Data , , 2014 . . p.7 - - 13 . . DOI: 10.1109/BigData.2014.7004416 http://doi.org/10.1109/BigData.2014.7004416 . .

SJ Kim , , , JH Lee . . Subtopic mining based on headmodifier relation and co-occurrence of intents using web documents . . LNCS , , 2013 . . 8138 179 - - 191 . . DOI: 10.1007/978-3-642-40802-1_22 http://doi.org/10.1007/978-3-642-40802-1_22 . .

Q Le , , , T Mikolov . . Distributed representations of sentences and documents . . Proc 31 st Int Conf on Machine Learning , , 2014 . . p.1188 - - 1196 . . . .

X Li , , , YY Wang , , , A Acero . . Learning query intent from regularized click graphs . . Proc 31 st Annual Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 2008 . . p.339 - - 346 . . DOI: 10.1145/1390334.1390393 http://doi.org/10.1145/1390334.1390393 . .

Y Liu , , , R Song , , , M Zhang , , , 等 . . Overview of the NTCIR-11 IMine task . . Proc 11 th NTCIR Conf , , 2014 . . p.8 - - 23 . . . .

C Luo , , , Y Liu , , , M Zhang , , , 等 . . Query recommendation based on user intent recognition . . J Chin Inform Process , , 2014 . . 28 ( ( 1 ): ): 64 - - 72 . . DOI: 10.3969/j.issn.1003-0077.2014.01.009 http://doi.org/10.3969/j.issn.1003-0077.2014.01.009 . .

T Mikolov , , , K Chen , , , G Corrado , , , 等 . . Efficient estimation of word representations in vector space , , 2013a . . https://arxiv.org/abs/1301.3781 https://arxiv.org/abs/1301.3781 , , . .

T Mikolov , , , WT Yih , , , G Zweig . . Linguistic regularities in continuous space word representations . . Proc NAACLHLT , , 2013b . . p.746 - - 751 . . . .

J Mitchell , , , M Lapata . . Composition in distributional models of semantics . . Cogn Sci , , 2010 . . 34 ( ( 8 ): ): 1388 - - 1429 . . DOI: 10.1111/j.1551-6709.2010.01106.x http://doi.org/10.1111/j.1551-6709.2010.01106.x . .

A Mnih , , , G Hinton . . Three new graphical models for statistical language modelling . . Proc 24 th Int Conf on Machine Learning , , 2007 . . p.641 - - 648 . . DOI: 10.1145/1273496.1273577 http://doi.org/10.1145/1273496.1273577 . .

F Radlinski , , , M Szummer , , , N Craswell . . Inferring query intent from reformulations and clicks . . Proc 19 th Int Conf on World Wide Web , , 2010 . . p.1171 - - 1172 . . DOI: 10.1145/1772690.1772859 http://doi.org/10.1145/1772690.1772859 . .

D Rafiei , , , K Bharat , , , A Shukla . . Diversifying web search results . . Proc 19 th Int Conf on World Wide Web , , 2010 . . p.781 - - 790 . . DOI: 10.1145/1772690.1772770 http://doi.org/10.1145/1772690.1772770 . .

T Sakai , , , R Song . . Evaluating diversified search results using per-intent graded relevance . . Proc 34 th Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 2011 . . p.1043 - - 1052 . . DOI: 10.1145/2009916.2010055 http://doi.org/10.1145/2009916.2010055 . .

T Sakai , , , Z Dou , , , T Yamamoto , , , 等 . . Overview of the NTCIR-10 INTENT-2 task . . Proc 10 th NTCIR Conf , , 2013 . . p.94 - - 123 . . . .

RLT Santos , , , C Macdonald , , , I Ounis . . Exploiting query reformulations for web search result diversification . . Proc 19 th Int Conf on World Wide Web , , 2010 . . p.881 - - 890 . . DOI: 10.1145/1772690.1772780 http://doi.org/10.1145/1772690.1772780 . .

R Socher , , , CC Lin , , , AY Ng , , , 等 . . Parsing natural scenes and natural language with recursive neural networks . . Proc 28 th Int Conf on Machine Learning , , 2011a . . p.129 - - 136 . . . .

R Socher , , , J Pennington , , , EH Huang , , , 等 . . Semisupervised recursive autoencoders for predicting sentiment distributions . . Proc Conf on Empirical Methods in Natural Language Processing, Association for Computational Linguistics , , 2011b . . p.151 - - 161 . . . .

R Song , , , Z Luo , , , JY Nie , , , 等 . . Identification of ambiguous queries in web search . . Inform Process Manag , , 2009 . . 45 ( ( 2 ): ): 216 - - 229 . . DOI: 10.1016/j.ipm.2008.09.005 http://doi.org/10.1016/j.ipm.2008.09.005 . .

R Song , , , M Zhang , , , T Sakai , , , 等 . . Overview of the NTCIR-9 INTENT task . . Proc NTCIR-9 Workshop Meeting , , 2011 . . p.82 - - 105 . . . .

W Song , , , Q Yu , , , ZH Xu , , , 等 . . Multi-aspect query summarization by composite query . . Proc 35 th Int ACM SIGIR Conf on Research and development in Information Retrieval , , 2012 . . p.325 - - 334 . . DOI: 10.1145/2348283.2348329 http://doi.org/10.1145/2348283.2348329 . .

W Song , , , Y Liu , , , L Liu , , , 等 . . Examining personalization heuristics by topical analysis of query log . . Int J Innov Comput Inform Contr , , 2016 . . 12 ( ( 5 ): ): 1745 - - 1760 . . . .

M Strohmaier , , , M Kröll , , , C Körner . . Intentional query suggestion: making user goals more explicit during search . . Proc Workshop on Web Search Click Data , , 2009 . . p.68 - - 74 . . DOI: 10.1145/1507509.1507520 http://doi.org/10.1145/1507509.1507520 . .

CJ Wang , , , YW Lin , , , MF Tsai , , , 等 . . Mining subtopics from different aspects for diversifying search results . . Inform Retriev , , 2013 . . 16 ( ( 4 ): ): 452 - - 483 . . DOI: 10.1007/s10791-012-9215-y http://doi.org/10.1007/s10791-012-9215-y . .

J Xu , , , WB Croft . . Query expansion using local and global document analysis . . Proc 19 th Annual Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 1996 . . p.4 - - 11 . . DOI: 10.1145/243199.243202 http://doi.org/10.1145/243199.243202 . .

M Yu , , , M Dredze . . Learning composition models for phrase embeddings . . Trans Assoc Comput Ling , , 2015 . . 3 227 - - 242 . . . .

FM Zanzotto , , , I Korkontzelos , , , F Fallucchi , , , 等 . . Estimating linear models for compositional distributional semantics . . Proc 23 rd Int Conf on Computational Linguistics , , 2010 . . p.1263 - - 1271 . . . .

HJ Zeng , , , QC He , , , Z Chen , , , 等 . . Learning to cluster web search results . . Proc 27 th Annual Int ACM SIGIR Conf on Research and Development in Information Retrieval , , 2004 . . p.210 - - 217 . . DOI: 10.1145/1008992.1009030 http://doi.org/10.1145/1008992.1009030 . .

Y Zhao , , , Z Liu , , , M Sun . . Phrase type sensitive tensor indexing model for semantic composition . . Proc 29 th AAAI Conf on Artificial Intelligence , , 2015 . . p.2195 - - 2201 . . . .

W Zheng , , , H Fang . . A comparative study of search result diversification methods . . 1 st Int Workshop on Diversity in Document Retrieval , , 2011 . . p.55 - - 62 . . . .

W Zheng , , , H Fang , , , C Yao , , , 等 . . Leveraging integrated information to extract query subtopics for search result diversification . . Inform Retriev , , 2014 . . 17 ( ( 1 ): ): 52 - - 73 . . DOI: 10.1007/s10791-013-9228-1 http://doi.org/10.1007/s10791-013-9228-1 . .

浏览量

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

暂无数据