Filters








9,945 Hits in 2.7 sec

Neural Document Expansion with User Feedback

Yue Yin, Chenyan Xiong, Cheng Luo, Zhiyuan Liu
2019 Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval - ICTIR '19  
This paper presents a neural document expansion approach (NeuDEF) that enriches document representations for neural ranking models.  ...  NeuDEF harvests expansion terms from queries which lead to clicks on the document and weights these expansion terms with learned attention.  ...  All neural ranking baselines leverage user feedback following Eq. 8. We implemented and compared with many document expansion baselines.  ... 
doi:10.1145/3341981.3344213 dblp:conf/ictir/YinXL019 fatcat:uexw6drg3bfohfghu4mjnlxoji

Incorporating Semantic Word Representations into Query Expansion for Microblog Information Retrieval

Bo Xu, Hongfei Lin, Yuan Lin, Kan Xu, Lin Wang, Jiping Gao
2019 Information Technology and Control  
In addition, we also combine the traditional pseudo-relevance feedback query expansion method with the proposed query expansion method.  ...  To enhance microblog information retrieval, we propose a novel query expansion method to enrich user queries with semantic word representations.  ...  [26] proposed to add user clicks as implicit feedback for secondary sorting of the document, and obtained better results. Kurland et al.  ... 
doi:10.5755/j01.itc.48.4.22487 fatcat:7nufcwuwabcyberduwvimkox4m

GQE-PRF: Generative Query Expansion with Pseudo-Relevance Feedback [article]

Minghui Huang, Dong Wang, Shuang Liu, Meizhen Ding
2021 arXiv   pre-print
Query expansion with pseudo-relevance feedback (PRF) is a powerful approach to enhance the effectiveness in information retrieval.  ...  Recently, with the rapid advance of deep learning techniques, neural text generation has achieved promising success in many natural language tasks.  ...  GQE-PRF Model Model Overview Given an initial user query, we are aiming at generating related expansion terms with the benefits of both local relevant documents and pre-trained natural language generation  ... 
arXiv:2108.06010v1 fatcat:e3sjq7d345fqdmn2apazmibi6e

Incorporating agent based neural network model for adaptive meta-search

Ying Xie, Dheerendranath Mundluru, Vijay V. Raghavan
2005 Proceedings of the 43rd annual southeast regional conference on - ACM-SE 43  
This approach uses an adaptive agent based neural network model to improve the quality of the search results by incorporating user relevance feedback in to the system.  ...  user queries.  ...  Query Expansion Algorithm In this subsection, we describe our query expansion algorithm. After a user gives feedback, the top agent constructs a new DNF query from the feedback information.  ... 
doi:10.1145/1167350.1167376 dblp:conf/ACMse/XieMR05 fatcat:p7pwhjrbqvcmpk2ulvks2qw3b4

Deep Neural Network and Pseudo Relevance Feedback Based Query Expansion

Abhishek Kumar Shukla, Sujoy Das
2022 Computers Materials & Continua  
Vocabulary terms are obtained from the top "k" initially retrieved documents using the Pseudo relevance feedback model and then they are trained using the skip-gram model to find the expansion terms for  ...  the user query.  ...  The user has only a fuzzy idea about what he/she is looking for. Due to this retrieval system retrieves irrelevant documents along with relevant documents.  ... 
doi:10.32604/cmc.2022.022411 fatcat:d3jjldoysjh3rpj7ailiyndh7e

Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval [article]

Xiao Wang, Craig Macdonald, Nicola Tonellotto, Iadh Ounis
2021 arXiv   pre-print
Pseudo-relevance feedback mechanisms, from Rocchio to the relevance models, have shown the usefulness of expanding and reweighting the users' initial queries using information occurring in an initial set  ...  Recently, dense retrieval -- through the use of neural contextual language models such as BERT for analysing the documents' and queries' contents and computing their relevance scores -- has shown a promising  ...  In particular, Neural PRF uses neural ranking models, such as DRMM [13] and KNRM [33] , to score the similarity of a document to a top-ranked feedback document.  ... 
arXiv:2106.11251v1 fatcat:uq5qmuoxmrb5dovez2zemz4vb4

The paraphrase search assistant

Peter G. Anick, Suresh Tipirneni
1999 Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '99  
We present a new linguistic approach to the construction of terminological feedback for use in interactive query refinement.  ...  Facet expansion: banking Term selection: "banking industry" Document selection: #6 Facet expansion: services Term selection: "financial services" Document selection: #1 : de500 Facet expansion: driver  ...  There is some evidence from recent studies comparing "opaque" and "penetrable" relevance feedback suggesting that allowing end-users to interact directly with terminological feedback improves not only  ... 
doi:10.1145/312624.312670 dblp:conf/sigir/AnickT99 fatcat:6limkwgpvjchdaud2et56czt3e

HQE: A hybrid method for query expansion

Lixin Han, Guihai Chen
2009 Expert systems with applications  
the most relevant web documents and their corresponding terms from these similar users' queries.  ...  The HQE method employs a combination of ontology-based collaborative filtering and neural networks to improve query expansion.  ...  Expansion terms employed are not based on frequencies in the top-ranked documents, similarly to local feedback, but on cooccurrences with the query terms.  ... 
doi:10.1016/j.eswa.2008.10.060 fatcat:y7xf5jxglrcopapaa32vbbx2da

RLIRank: Learning to Rank with Reinforcement Learning for Dynamic Search

Jianghong Zhou, Eugene Agichtein
2020 Proceedings of The Web Conference 2020  
To support this dynamic ranking paradigm effectively, search result ranking must incorporate both the user feedback received, and the information displayed so far.  ...  To incorporate the user's feedback, we develop a word-embedding variation of the classic Rocchio Algorithm, to help guide the ranking towards the high-value documents.  ...  Figure 1 : 1 Flow of Dynamic Search with user feedback. The returned results are dynamically re-ranked based on the user's feedback. Figure 1 1 illustrates the dynamic search process.  ... 
doi:10.1145/3366423.3380047 dblp:conf/www/ZhouA20 fatcat:hivnsj2zlbdkjcbnhttmc3gh4y

Query expansion based on relevance feedback and latent semantic analysis

Marziea Rahimi, Morteza Zahedi
2014 Journal of Artificial Intelligence and Data Mining  
The method is evaluated and compared with the Rocchio relevance feedback.  ...  This method which is a combination of relevance feedback and latent semantic analysis, finds the relative terms to the topics of user original query based on relevant documents selected by the user in  ...  The proposed method consists of three steps: 1) User initial search, 2) User relevance feedback and 3) Query expansion.  ... 
doi:10.22044/jadm.2014.188 doaj:0fdc398bda9d47bdaddeebd63a7f04b6 fatcat:svg4p6mwm5dhlcttxpiqd2ubv4

Web document clustering using a hybrid neural network

M.Shamim Khan, Sebastian W Khor
2004 Applied Soft Computing  
This paper describes a method developed for the automatic clustering of World Wide Web documents, according to their relevance to the user's information needs, by using a hybrid neural network.  ...  and the user.  ...  The document clustering and ranking technique developed by us is meant to form an intelligent interface between the typical Web search engine and the user.  ... 
doi:10.1016/j.asoc.2004.02.003 fatcat:wxtx7t6fgjc5jgfb5tp3kiypnq

Feature Weighting in Finding Feedback Documents for Query Expansion in Biomedical Document Retrieval

Jainisha Sankhavara
2020 SN Computer Science  
This proposed approach uses an NLP-based feature weighting technique with classification and clustering method on the documents and identifies relevant documents for feedback.  ...  Finding good feedback documents for query expansion is a well-known problem in the field of information retrieval.  ...  The comparison of results of two feature weighting techniques with the results of original queries without expansion, expansion with relevance feedback and expansion with feedback document discovery without  ... 
doi:10.1007/s42979-020-0069-x fatcat:gqczonzbcvc5fofu3dp7mc7dce

Query modification and expansion in a network with adaptive architecture

K. L. Kwok
1991 Proceedings of the 14th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '91  
This paper shows how a newtwork view of probabilistic information indexing and retrieval with components may implement query expansion and modification (based on user relevance feedback) by growing new  ...  Experimental results with two collections and partial feedback confirm that the process can lead to much improved performance. Learning from irrelvant documents however was not effective.  ...  Conclusion No Feedback I both will serve as basis for comparison modification with expansion for both relevant or irrelevant with feedback [CroR3] Croft, W. B (1983).  ... 
doi:10.1145/122860.122879 dblp:conf/sigir/Kwok91 fatcat:f6lgf2ajzncrnpuoal74hynigm

Rethinking Query Expansion for BERT Reranking [chapter]

Ramith Padaki, Zhuyun Dai, Jamie Callan
2020 Lecture Notes in Computer Science  
Recent studies have shown promising results of using BERT for Information Retrieval with its advantages in understanding the text content of documents and queries.  ...  We find that traditional word-based query expansion is not entirely applicable, and provide insight into methods that produce better experimental results.  ...  These allow users to more effectively express their information need and help systems to better disambiguate documents with similar-looking content.  ... 
doi:10.1007/978-3-030-45442-5_37 fatcat:yhwdokljpjc33p62t4frshefd4

Relevance and reinforcement in interactive browsing

Anton Leuski
2000 Proceedings of the ninth international conference on Information and knowledge management - CIKM '00  
We describe an interactive relevance feedback agent that analyzes the inter-document similarities and can help the user to locate the interesting information quickly.  ...  We show how such an agent can be designed and improved by using neural networks and reinforcement learning.  ...  The highest numbers reported earlier did not much exceed the interactive relevance feedback baseline with 10 terms expansion (Table 1 , column 3).  ... 
doi:10.1145/354756.354809 dblp:conf/cikm/Leuski00 fatcat:vrt77ofqo5b5noiefy3re2zgpy
« Previous Showing results 1 — 15 out of 9,945 results