Article
Computer Science, Artificial Intelligence
Irfan Ullah, Sikandar Alam, Zafar Ali, Mahmood Khan, Fouzia Jabeen, Shah Khusro
Summary: The role of query formulation in retrieving relevant search results is important in Information Retrieval (IR) systems. Researchers have experimented with various approaches such as using topic fields, reducing verbose queries, and query expansion. However, there is a lack of survey or review articles on query formulation in the domain of book search. This paper fills this gap by reviewing research publications from 2007 to 2022, summarizing findings using a well-defined theoretical framework, identifying current trends, and providing a cross-comparison of best-performing methods. It has implications for researchers in IR and book search.
ARTIFICIAL INTELLIGENCE REVIEW
(2023)
Article
Computer Science, Information Systems
Xiao Wang, Craig Macdonald, Iadh Ounis
Summary: Pseudo-relevance feedback is a classical technique to improve search engine retrieval effectiveness. Past external expansion methods have only been studied for sparse retrieval methods, and the effectiveness for recent dense retrieval methods remains under-investigated. This study examines the application of dense external expansion to improve zero-shot retrieval effectiveness.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Computer Science, Artificial Intelligence
Min Pan, Quanli Pei, Yu Liu, Teng Li, Ellen Anne Huang, Junmei Wang, Jimmy Xiangji Huang
Summary: This study proposes a semantic-based Pseudo-relevance Feedback model (SPRF) that leverages ConceptNet to enhance the selection of query expansion terms for information retrieval. The experimental results demonstrate that SPRF achieves good performance and shows advantages over baseline models and neural network-based methods.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Bilel Elayeb, Oussama Ben Khiroun
Summary: In this paper, we propose a new architecture for a possibilistic mono- and cross-language information retrieval (IR/CLIR) system. The system allows for query disambiguation, expansion, and translation processes, and overcomes the challenges of uncertainty and imprecision in IR/CLIR using possibility theory. By utilizing a co-occurrence graph representation, we quantify the similarity between query terms and their semantically close words or possible meanings. Our possibilistic approaches show significant improvements compared to state-of-the-art IR/CLIR works.
INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING
(2023)
Article
Computer Science, Artificial Intelligence
Sarah Dahir, Abderrahim El Qadi, Hamid Bennis
Summary: Query Expansion aims to address the vocabulary mismatch issue in Information Retrieval Systems by adding new terms to the initial user query. Linked Data can be used as a valuable resource for providing additional expansion features. Selecting the right candidate terms for expansion is a key issue in Query Expansion.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Chemistry, Multidisciplinary
Sergio Silva, Adrian Seara Vieira, Pedro Celard, Eva Lorenzo Iglesias, Lourdes Borrajo
Summary: Information retrieval aims to obtain relevant information for users, with query expansion techniques used to improve retrieval by adding similar meaningful terms. A supervised query expansion technique based on Multinomial Naive Bayes demonstrated improved performance in extracting relevant terms from initial query documents.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Information Systems
Ayman A. Taan, Shafiq Ur Rehman Khan, Ali Raza, Ayaz Muhammad Hanif, Hira Anwar
Summary: This study investigated the performance of different Information Retrieval models in Cross-Language Information Retrieval (CLIR) system, as well as the impact of query length and query expansion models on effective retrieval. The results showed that query length has an influence on retrieval effectiveness, leading to the suggestion of an appropriate query length and the best query expansion and retrieval models for Arabic CLIR system.
Article
Computer Science, Information Systems
Min Pan, Junmei Wang, Jimmy X. Huang, Angela J. Huang, Qi Chen, Jinguang Chen
Summary: In this study, a probabilistic framework based on the classic Rocchio model is proposed to incorporate sentence-level semantics into PRF using Bidirectional Encoder Representations from Transformers (BERT). Experimental results show that the improved models achieve significant improvements over baseline models, providing a promising avenue for integrating sentence-level semantics into PRF.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Computer Science, Information Systems
Dilip Kumar Sharma, Rajendra Pamula, D. S. Chauhan
Summary: This paper presents a method for query enhancement by analyzing the impact of abbreviation resolution, lexical variation, synonyms, n-gram pseudo relevance feedback, and co-occurrence on the baseline query expansion approaches. The experimental results show improvement in the performance of query expansion in terms of mean average precision, F-measure, and precision-recall curve.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Hiteshwar Kumar Azad, Akshay Deepak, Chinmay Chakraborty, Kumar Abhishek
Summary: Query expansion is a technique used in information retrieval to address word mismatch between a user's query and the target information. Existing weighting techniques often fail to capture the term-term relationship and term to the whole query relationship accurately, resulting in low retrieval effectiveness. This study proposes a query expansion approach based on tf-idf, k-nearest neighbor (kNN) based cosine similarity, and correlation score to address this issue. The proposed model, called web knowledge based query expansion (WKQE), achieves significant improvement in retrieval performance compared to other related approaches.
PATTERN RECOGNITION LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Dilip Kumar Sharma, Rajendra Pamula, D. S. Chauhan
Summary: This paper provides a comprehensive survey on semantic-based query expansion methods proposed by researchers, discussing the merits and demerits of each technique in detail. It emphasizes the importance of computational intelligence in automatic query expansion for advanced information processing.
EVOLUTIONARY INTELLIGENCE
(2021)
Article
Computer Science, Information Systems
Shariq Bashir, Daphne Teck Ching Lai, Owais Ahmed Malik
Summary: Search engines store users' queries in a query log for personalized information retrieval. Private web search (PWS) is a technique that allows users to retrieve information without revealing their true search queries. This article proposes a new query obfuscation technique based on proxy terms, which can effectively protect users' privacy in web search.
Article
Computer Science, Hardware & Architecture
Ram Kumar, S. C. Sharma
Summary: Query expansion is an important approach to improve data retrieval efficiency. Existing methods do not work well for all types of queries, especially phrase and individual queries. This paper proposes a new query expansion technique that analyzes different data sources, and introduces the IAOCOOT algorithm to retrieve semantic aspects that match the query.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Hamidreza Mahini, Hamidreza Navidi, Fatemeh Babaei, Seyyedeh Mobarakeh Mousavirad
Summary: This paper introduces a novel inventory sharing algorithm based on population game and evolutionary dynamics, and confirms its effectiveness through theoretical derivation and implementation in MATLAB.
SWARM AND EVOLUTIONARY COMPUTATION
(2021)
Article
Biology
Elizabeth A. Tripp, Feng Fu, Scott D. Pauls
Summary: Biological systems have various time-keeping mechanisms, and understanding the evolutionary development of these mechanisms is crucial. This study introduces a new evolutionary game theoretic framework to model the behavior and evolution of systems of coupled oscillators, shedding light on the relationship between synchronization and connectivity.
PROCEEDINGS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES
(2022)