381 Hits in 4.8 sec

QR2: A Third-party Query Reranking Service Over Web Databases [article]

Yeshwanth D. Gunasekaran, Abolfazl Asudeh, Sona Hasani, Nan Zhang, Ali Jaoua, Gautam Das
2018 arXiv   pre-print
Despite the extensive efforts on designing better ranking mechanisms, in practice, many such databases fail to address the diverse and sometimes contradicting preferences of users.  ...  In this paper, we present QR2, a third-party service that uses nothing but the public search interface of a web database and enables the on-the-fly processing of queries with any user-specified ranking  ...  Any findings, conclusions, or recommendations expressed in this material are those of the authors and do not necessarily reflect the views of the sponsors listed above.  ... 
arXiv:1807.05258v1 fatcat:vmek4ciw2bcfva4knvimftc4ly

Understanding Intrinsic Diversity in Web Search

Karthik Raman, Paul N. Bennett, Kevyn Collins-Thompson
2014 ACM Transactions on Information Systems  
However, a significant fraction of user queries are part of more complex tasks [Jones and Klinkner 2008] which span multiple queries across one or more search sessions Kotov et al. 2011 ].  ...  An ideal search engine would not only retrieve relevant results for a user's particular query but also be able to identify when the user is engaged in a more complex task and aid the user in completing  ...  Ultimately our goal is to enable a search engine to customize the search results for intrinsic diversity only when appropriate, while providing at least the same level of relevance on tasks predicted to  ... 
doi:10.1145/2629553 fatcat:2qe3cq7elndh7dv2mhvsfgfuji

A Personalized Graph-Based Document Ranking Model Using a Semantic User Profile [chapter]

Mariam Daoud, Lynda Tamine, Mohand Boughanem
2010 Lecture Notes in Computer Science  
The overload of the information available on the web, held with the diversity of the user information needs and the ambiguity of their queries have led the researchers to develop personalized search tools  ...  Results show the effectiveness of our personalized graph-based ranking model compared to Yahoo 1 search results.  ...  As our approach is based on personalizing search across sessions defined by a sequence of related queries, we have selected 25 user search sessions for all the 10 users as follows: -Each session contains  ... 
doi:10.1007/978-3-642-13470-8_17 fatcat:ytjxgzndr5axnjej3k7akykede

Enriching information retrieval

Paul N. Bennett, Khalid El-Arini, Thorsten Joachims, Krysta M. Svore
2012 SIGIR Forum  
, personalization, diversification, and faceted search.  ...  Documents no longer exist on their own; they are connected to other documents, they are associated with users and their position in a social network, and they can be mapped onto a variety of ontologies  ...  Additionally, the idea of providing a lower-level API for a retrieval system (potentially giving developers the ability to produce their own reranked results) was floated as a way to spawn innovation.  ... 
doi:10.1145/2093346.2093355 fatcat:77mxfekktbhqtfhwpldmkovs6m

Did You Say U2 or YouTube?

Milad Shokouhi, Umut Ozertem, Nick Craswell
2016 Proceedings of the 25th International Conference on World Wide Web - WWW '16  
This can give a large amount of free training data that matches the exact characteristics of real incoming voice searches and the implicit transcriptions can better reflect the needs of real users because  ...  Web search via voice is becoming increasingly popular, taking advantage of recent advances in automatic speech recognition.  ...  The search session starts when the user issues the query different kinds of graphs by voice.  ... 
doi:10.1145/2872427.2882994 dblp:conf/www/ShokouhiOC16 fatcat:fridknym4jcq7nitincxj6r76u

A vlHMM approach to context-aware search

Zhen Liao, Daxin Jiang, Jian Pei, Yalou Huang, Enhong Chen, Huanhuan Cao, Hang Li
2013 ACM Transactions on the Web  
The experiment results validate the effectiveness of vlHMM in the applications of document reranking, URL recommendation, and query suggestion. 22:2 Z.  ...  Consider the search sessions in Table I , which are several sessions of different users from Bing (  ...  The top search results of the last query are labeled as five levels: perfect, excellent, good, fair, and bad.  ... 
doi:10.1145/2490255 fatcat:isxpjrgkgbdcpf7hrm6r5h2zla

Leveraging user comments for aesthetic aware image search reranking

Jose San Pedro, Tom Yeh, Nuria Oliver
2012 Proceedings of the 21st international conference on World Wide Web - WWW '12  
users searching for photographs on the Web.  ...  This paper studies the influence of visual aesthetic quality in search results as a complementary attribute to relevance.  ...  We also plan to study the scalability of the solution as well as the viability of this approach to model aesthetics from user opinions in non-specialized communities, where comments could be less technical  ... 
doi:10.1145/2187836.2187896 dblp:conf/www/PedroYO12 fatcat:yl5s5opjpvdk7bknw46vmzce4u

From query to question in one click

Gideon Dror, Yoelle Maarek, Avihai Mejer, Idan Szpektor
2013 Proceedings of the 22nd international conference on World Wide Web - WWW '13  
Years of research focused on providing the best user experience for the data available to the search engine.  ...  In Web search, users may remain unsatisfied for several reasons: the search engine may not be effective enough or the query might not reflect their intent.  ...  We limited ourselves to the 3 best suggestions as this seems to be a reasonable size of a list to be shown to users, be it on the search result page or on the CQA site itself.  ... 
doi:10.1145/2488388.2488423 dblp:conf/www/DrorMMS13 fatcat:shcizephvfb5pgs6ecsztkxxn4

Using web-graph distance for relevance feedback in web search

Sergei Vassilvitskii, Eric Brill
2006 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '06  
We study the effect of user supplied relevance feedback in improving web search results.  ...  Yahoo's mindset search [21] lets users rerank the results, giving more influence to "Shopping" or "Research" URLs. Other work has explored the space of query suggestion.  ...  The web-graph reranker has several attractive properties: • Search engines strive for diversity in search results.  ... 
doi:10.1145/1148170.1148199 dblp:conf/sigir/VassilvitskiiB06 fatcat:xllgqtn5nndrbopwyowpugwfza

Conditional Sequential Slate Optimization [article]

Yipeng Zhang, Mingjian Lu, Saratchandra Indrakanti, Manojkumar Rangasamy Kannadasan, Abraham Bagherjeiran
2021 arXiv   pre-print
The top search results matching a user query that are displayed on the first page are critical to the effectiveness and perception of a search system.  ...  The proposed method can be applied to practical real world problems such as enforcing diversity in e-commerce search results, mitigating bias in top results and personalization of results.  ...  The aim of reranking, in this case, is to ensure diversity within the search results on the first page.  ... 
arXiv:2108.05618v2 fatcat:fwjw5wkoifcxtpaofxvgk7w76y

A Survey on Video Recommendation and Ranking in Video Search Engine

Nikhil Dhonge
2015 International Journal on Recent and Innovation Trends in Computing and Communication  
In this paper, we proposed a re-positioning strategy that enhances the execution of semantic feature indexing and recovery, by re-assessing the scores of the shots by the homogeneity and the way of the  ...  This paper presents a recommender framework which has been created to study examination addresses in the field of news feature suggestion and personalization.  ...  Video Search Reranking via Information Bottleneck Principle (Winston H.  ... 
doi:10.17762/ijritcc2321-8169.150216 fatcat:iupj5yebwjd7xbid3dafhzcx5u

Multiple Queries as Bandit Arms

Cheng Li, Paul Resnick, Qiaozhu Mei
2016 Proceedings of the 25th ACM International on Conference on Information and Knowledge Management - CIKM '16  
In the presence of rate limits, the active queries take turns accessing the index to retrieve another "page" of results. Turns are assigned by a multi-armed bandit based on user feedback.  ...  Significant improvement is observed both when the subtopic queries are known in advance and when the queries are generated in a user-interactive process.  ...  This work is partially supported by the National Science Foundation under grant numbers IIS-0968489 and IIS-1054199 and by the National Institutes of Health under grant number NLM 2R01LM010681-05.  ... 
doi:10.1145/2983323.2983816 dblp:conf/cikm/LiRM16 fatcat:d4ijehk4q5dizixcgjjytxhxwq

Combining Interaction and Content for Feedback-Based Ranking [chapter]

Emanuele Di Buccio, Massimo Melucci, Dawei Song
2011 Lecture Notes in Computer Science  
We report that the effectiveness of the combination of user interaction for implicit feedback depends on whether document re-ranking is on a single-user or a user-group basis.  ...  Experiments on a TREC Web test collection have been carried out and the experimental results are illustrated.  ...  the 7th Framework Program of the European commission.  ... 
doi:10.1007/978-3-642-21353-3_5 fatcat:cmbyyxxxyfbifeyxivbstv3lh4

TREC CAsT 2019: The Conversational Assistance Track Overview [article]

Jeffrey Dalton, Chenyan Xiong, Jamie Callan
2020 arXiv   pre-print
A common theme through the runs is the use of BERT-based neural reranking methods.  ...  The results show a gap between automatic systems and those using the manually resolved utterances, with a 35% relative improvement of manual rewrites over the best automatic system.  ...  We first present results macro-averaged at the level of every turn independently.  ... 
arXiv:2003.13624v1 fatcat:ful7udqmmvfcfom65oxc76dq24

Multimedia search reranking

Tao Mei, Yong Rui, Shipeng Li, Qi Tian
2014 ACM Computing Surveys  
Such a problem is challenging because the initial search results often have a great deal of noise.  ...  The explosive growth and widespread accessibility of community contributed media content on the Internet have led to a surge of research activity in multimedia search.  ...  This work was also supported in part by National Science Foundation of China (NSFC) 61128007.  ... 
doi:10.1145/2536798 fatcat:6kmga3jo4fa2tp4354wukfuzja
« Previous Showing results 1 — 15 out of 381 results