A query term re-weighting approach using document similarity

Karisani, Payam; Rahgozar, Maseud; Oroumchian, Farhad

doi:10.1016/j.ipm.2015.09.002

Cited by 35 publications

(13 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The queries prepared by the bioCADDIE organizers are relatively verbose , averaging 15.8 terms (words) per query. Query term weighting and keyword detection for such verbose queries have shown to be effective in previous work ( 8 , 9 ). We used one such technique, called Weighted Information Gain ( WIG ), introduced by Zhou and Croft in reference ( 10 ), to detect the most important keywords in the query and boost (assign a higher weight to) these terms.…”

Section: Methodology: Retrieval System Architecture and Implementatiomentioning

confidence: 97%

Probabilistic and machine learning-based retrieval approaches for biomedical dataset retrieval

2018

Self Cite

View full text Add to dashboard Cite

The bioCADDIE dataset retrieval challenge brought together different approaches to retrieval of biomedical datasets relevant to a user’s query, expressed as a text description of a needed dataset. We describe experiments in applying a data-driven, machine learning-based approach to biomedical dataset retrieval as part of this challenge. We report on a series of experiments carried out to evaluate the performance of both probabilistic and machine learning-driven techniques from information retrieval, as applied to this challenge. Our experiments with probabilistic information retrieval methods, such as query term weight optimization, automatic query expansion and simulated user relevance feedback, demonstrate that automatically boosting the weights of important keywords in a verbose query is more effective than other methods. We also show that although there is a rich space of potential representations and features available in this domain, machine learning-based re-ranking models are not able to improve on probabilistic information retrieval techniques with the currently available training data. The models and algorithms presented in this paper can serve as a viable implementation of a search engine to provide access to biomedical datasets. The retrieval performance is expected to be further improved by using additional training data that is created by expert annotation, or gathered through usage logs, clicks and other processes during natural operation of the system. Database URL: https://github.com/emory-irlab/biocaddie

show abstract

Section: Methodology: Retrieval System Architecture and Implementatiomentioning

confidence: 97%

Probabilistic and machine learning-based retrieval approaches for biomedical dataset retrieval

2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Pseudo-relevance feedback (PRF) is a method that used in a branch of automatic query modification technique. PRF assumes that the initial retrieved documents are relevant and then it uses these documents to find more relevant terms to the query or it just re-weighs the original query terms (Karisani et al, 2016). Word embeddings (WE) is a common name to a set of techniques to model languages and extract interested features.…”

Section: Related Workmentioning

confidence: 99%

Query Sense Discovery Approach to Realize the User's Search Intent

Chenaina

Neji

Shoeb

2021

International Journal of Information Retrieval Research

View full text Add to dashboard Cite

The main goal of information retrieval is getting the most relevant documents to a user’s query. So, a search engine must not only understand the meaning of each keyword in the query but also their relative senses in the context of the query. Discovering the query meaning is a comprehensive and evolutionary process; the precise meaning of the query is established as developing the association between concepts. The meaning determination process is modeled by a dynamic system operating in the semantic space of WordNet. To capture the meaning of a user query, the original query is reformulating into candidate queries by combining the concepts and their synonyms. A semantic score characterizing the overall meaning of such queries is calculated, the one with the highest score was used to perform the search. The results confirm that the proposed "Query Sense Discovery" approach provides a significant improvement in several performance measures.

show abstract

“…Finding of neighbors. To calculate the neighbors of the input query, the document similarity measure [20] is used, in which the matching process is done between the input query and the feature library. Because of the consideration of both frequency and similarity of the nearest documents, the similarity measure is applied to find similar values.…”

Section: Semantic Classifier Based Featuresmentioning

confidence: 99%

LionRank: lion algorithm-based metasearch engines for re-ranking of webpages

Vijaya

Chander

2018

Sci. China Inf. Sci.

View full text Add to dashboard Cite

Due to the rapid growth of the web, the process of collecting the relevant web pages based on the user query is one of the major challenging tasks in recent days. Hence, it is very complicated for the users to know the most relevant information even though various search engines are widely employed. To deal with users' trouble in identifying the relevant information from the web, we have proposed a meta-lion search engine to capture and analyze the ranking scores of various search engines and thereby, generate the re-ranked score results. Accordingly, LionRank, a lion algorithm-based meta-search engine is proposed for the re-ranking of the web pages. Here, different features like text based, factor based, rank based and classifier based features are used by the underlying search engines. In classifier based feature extraction, we have used the fuzzy integrated extended nearest neighbor (FENN) classifier to include the semantics in feature extraction. Moreover, an intelligent re-ranking process is proposed based on the lion algorithm to fuse the features scores optimally. Finally, the results of the proposed LionRank is analyzed with the web page database collected through four benchmark queries, and the quantitative performance are analyzed using precision, recall, and F-score. From the results, we proved that the proposed LionRank obtained the maximum F-score of 81% as compared with that of existing search engines like QuadRank, Outrank, Google, Yahoo, and Bing.

show abstract

A query term re-weighting approach using document similarity

Cited by 35 publications

References 6 publications

Probabilistic and machine learning-based retrieval approaches for biomedical dataset retrieval

Probabilistic and machine learning-based retrieval approaches for biomedical dataset retrieval

Query Sense Discovery Approach to Realize the User's Search Intent

LionRank: lion algorithm-based metasearch engines for re-ranking of webpages

Contact Info

Product

Resources

About