Improving retrieval performance by relevance feedback

Salton, Gerard; Buckley, Chris

doi:10.1002/(sici)1097-4571(199006)41:4<288::aid-asi8>3.0.co;2-h

Cited by 1,080 publications

(596 citation statements)

References 14 publications

Supporting

Mentioning

573

Contrasting

Unclassified

Order By: Relevance

“…PRF assumes the top n documents from initial retrieval as being relevant and uses these pseudo-relevant documents to refine the query for the next retrieval. Due to its automatic manner and effective performance, PRF has been widely applied in different IR frameworks like vector space models [8], probabilistic IR [9] and language modeling [10].…”

Section: A Pseudo Relevance Feedbackmentioning

confidence: 53%

“…Since real user feedbacks are hard to obtain, Pseudo-Relevance Feedback (PRF) is used as an alternative solution [8]. PRF assumes the top n documents from initial retrieval as being relevant and uses these pseudo-relevant documents to refine the query for the next retrieval.…”

Section: A Pseudo Relevance Feedbackmentioning

confidence: 99%

“…Top n terms (n=5, 10, 15, 20 or 25) with highest weights are selected for query expansion. By changing query term weights using formula (8), the MAP score is improved 7%. With n=10, the query expansion method using the formula FW2 gives the best MAP score of 0.425, which is 112% of the baseline and 104% of CW configuration.…”

Section: A Test Configurationmentioning

confidence: 99%

See 2 more Smart Citations

Improve Cross Language Information Retrieval With Pseudo-Relevance Feedback

Giang¹,

Hung²,

Pháp³

2016

Fair - Nghiên Cứu Cơ Bản Và Ứng Dụng Công Nghệ Thông Tin 2015

View full text Add to dashboard Cite

show abstract

Section: A Pseudo Relevance Feedbackmentioning

confidence: 53%

Section: A Pseudo Relevance Feedbackmentioning

confidence: 99%

See 1 more Smart Citation

Improve Cross Language Information Retrieval With Pseudo-Relevance Feedback

Giang¹,

Hung²,

Pháp³

2016

Fair - Nghiên Cứu Cơ Bản Và Ứng Dụng Công Nghệ Thông Tin 2015

View full text Add to dashboard Cite

show abstract

“…Query expansion techniques select suggestions for query refinement either interactively or automatically [11]. For instance, relevance feedback gathers judgments obtained from the users on sample results obtained from an initial query [25,26,19].…”

Section: Related Workmentioning

confidence: 99%

Query Refinement Using Conversational Context: A Method and an Evaluation Resource

Habibi

Popescu-Belis

2015

Natural Language Processing and Information Systems

View full text Add to dashboard Cite

Abstract. This paper introduces a query refinement method applied to queries asked by users during a meeting or a conversation. Current approaches suffer from poor quality to achieve this goal, but we argue that their performance could be improved by focusing on the local context of the conversation. The proposed technique first represents the local context by extracting keywords from the transcript of the conversation. It then expands the queries with keywords that best represent the topic of the query (e.g. pairs of expansion keywords together with a weight indicating their topical similarity to the query). Moreover, we present a dataset called AREX and an evaluation metric. We compared our query expansion approach with other methods, on topics extracted from the AREX dataset and based on relevance judgments collected in a crowdsourcing experiment. The comparisons indicate the superiority of our method on both manual and ASR transcripts of the AMI Meeting Corpus.

show abstract

“…Many experiments on relevance feedback empirically show that it improves retrieval performance dramatically [12]. Pseudo relevance feedback typically adds new terms to the initial query by assuming that the several top documents in the initial ranked output are relevant.…”

Section: Related Workmentioning

confidence: 99%

Large Scale Unstructured Document Classification Using Unlabeled Data and Syntactic Information

Park¹,

Zhang²

2003

Advances in Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

Abstract. Most document classification systems consider only the distribution of content words of the documents, ignoring the syntactic information underlying the documents though it is also an important factor. In this paper, we present an approach for classifying large scale unstructured documents by incorporating both lexical and syntactic information of documents. For this purpose, we use the co-training algorithm, a partially supervised learning algorithm, in which two separated views for the training data are employed and the small number of labeled data are augmented by a large number of unlabeled data. Since both lexical and syntactic information can play roles of separated views for the unstructured documents, the co-training algorithm enhances the performance of document classification using both of them and a large number of unlabeled documents. The experimental results on Reuters-21578 corpus and TREC-7 filtering documents show the effectiveness of unlabeled documents and the use of both lexical and syntactic information.

show abstract

Improving retrieval performance by relevance feedback

Cited by 1,080 publications

References 14 publications

Improve Cross Language Information Retrieval With Pseudo-Relevance Feedback

Improve Cross Language Information Retrieval With Pseudo-Relevance Feedback

Query Refinement Using Conversational Context: A Method and an Evaluation Resource

Large Scale Unstructured Document Classification Using Unlabeled Data and Syntactic Information

Contact Info

Product

Resources

About