Automatic query expansion has long been suggested as a technique for dealing with the fundamental issue of word mismatch in information retrieval. A number of approaches to expansion have been studied and, more recently, attention has focused on techniques that analyze the corpus to discover word relationship (global techniques) and those that analyze documents retrieved by the initial query ( local feedback). In this paper, we compare the effectiveness of these approaches and show that, although global analysis haa some advantages, local analysia is generally more effective. We also show that using global analysis techniques.

/pdf/quary-expansion-using-local-and-global-document-analysis-1cb5v2zqss.pdf

Quary Expansion Using Local and Global Document Analysis

The relative ineffectiveness of information retrieval systems is largely caused by the inaccuracy with which a query formed by a few keywords models the actual user information need. One well known method to overcome this limitation is automatic query expansion (AQE), whereby the user’s original query is augmented by new features with a similar meaning. AQE has a long history in the information retrieval community but it is only in the last years that it has reached a level of scientific and experimental maturity, especially in laboratory settings such as TREC. This survey presents a unified view of a large number of recent approaches to AQE that leverage various data sources and employ very different principles and techniques. The following questions are addressed. Why is query expansion so important to improve search effectiveness? What are the main steps involved in the design and implementation of an AQE component? What approaches to AQE are available and how do they compare? Which issues must still be resolved before AQE becomes a standard component of large operational information retrieval systems (e.g., search engines)?

/pdf/a-survey-of-automatic-query-expansion-in-information-30cfvdlacg.pdf

A Survey of Automatic Query Expansion in Information Retrieval

Information retrieval systems traditionally rely on textual keywords to index and retrieve documents. Keyword-based retrieval may return inaccurate and incomplete results when different keywords are used to describe the same concept in the documents and in the queries. Furthermore, the relationship between these related keywords may be semantic rather than syntactic, and capturing it thus requires access to comprehensive human world knowledge. Concept-based retrieval methods have attempted to tackle these difficulties by using manually built thesauri, by relying on term cooccurrence data, or by extracting latent word relationships and concepts from a corpus. In this article we introduce a new concept-based retrieval approach based on Explicit Semantic Analysis (ESA), a recently proposed method that augments keyword-based text representation with concept-based features, automatically extracted from massive human knowledge repositories such as Wikipedia. Our approach generates new text features automatically, and we have found that high-quality feature selection becomes crucial in this setting to make the retrieval more focused. However, due to the lack of labeled data, traditional feature selection methods cannot be used, hence we propose new methods that use self-generated labeled training data. The resulting system is evaluated on several TREC datasets, showing superior performance over previous state-of-the-art results.

/pdf/concept-based-information-retrieval-using-explicit-semantic-2ysazemmls.pdf

Concept-Based Information Retrieval Using Explicit Semantic Analysis

With the ever increasing size of the web, relevant information extraction on the Internet with a query formed by a few keywords has become a big challenge. Query Expansion (QE) plays a crucial role in improving searches on the Internet. Here, the user’s initial query is reformulated by adding additional meaningful terms with similar significance. QE – as part of information retrieval (IR) – has long attracted researchers’ attention. It has become very influential in the field of personalized social document, question answering, cross-language IR, information filtering and multimedia IR. Research in QE has gained further prominence because of IR dedicated conferences such as TREC (Text Information Retrieval Conference) and CLEF (Conference and Labs of the Evaluation Forum). This paper surveys QE techniques in IR from 1960 to 2017 with respect to core techniques, data sources used, weighting and ranking methodologies, user participation and applications – bringing out similarities and differences.

Query expansion techniques for information retrieval: A survey

During the last decades huge amounts of data have been collected in clinical databases representing patients' health states (e.g., as laboratory results, treatment plans, medical reports). Hence, digital information available for patient-oriented decision making has increased drastically but is often scattered across different sites. As as solution, personal health record systems (PHRS) are meant to centralize an individual's health data and to allow access for the owner as well as for authorized health professionals. Yet, expert-oriented language, complex interrelations of medical facts and information overload in general pose major obstacles for patients to understand their own record and to draw adequate conclusions. In this context, recommender systems may supply patients with additional laymen-friendly information helping to better comprehend their health status as represented by their record. However, such systems must be adapted to cope with the specific requirements in the health domain in order to deliver highly relevant information for patients. They are referred to as health recommender systems (HRS). In this article we give an introduction to health recommender systems and explain why they are a useful enhancement to PHR solutions. Basic concepts and scenarios are discussed and a first implementation is presented. In addition, we outline an evaluation approach for such a system, which is supported by medical experts. The construction of a test collection for case-related recommendations is described. Finally, challenges and open issues are discussed.

https://www.mdpi.com/1660-4601/11/3/2580/pdf

Health recommender systems: concepts, requirements, technical basics and challenges

Concept based search is a method that enhances information retrieval systems using semantic relationships. The recall in concept based search is relatively low. That low recall comes from the fact that it is not easy to represent a concept completely. Query expansion intends to fill a gap because concept representation is always partial. Query expansion improves the recall. In this paper we present an expansion method for a concept based information retrieval. Our method uses semantic relatedness to extend user query through an undirected graph of concepts.

Concept Based Query Expansion

Semantic Relatedness is widely used in various domains such as DNA sequence analysis, knowledge representation, natural language processing, data mining, information retrieval, information flow etc… Computing semantic similarity between two entities is a non-trivial task. There are many ways to define semantic similarity. Some measures have been proposed combining both statistical information and lexical similarity. It is difficult for a measure that performs well in a given domain to be applied with accuracy in another domain. A similarity measure may perform better with one language than another. Word is supposed to be not only similar to itself but also to some of its synonyms in a given context, and some words with common roots. Our approach is designed to perform query matching and compute semantic relatedness using word occurrences. It performs better than classical measures like TF-IDF, Cosine etc… Although it is not a metric, the proposed similarity measure can be used for a wide range of content analysis tasks based on semantic distance and its efficacy has been demonstrated. The measure is not corpus dependent so it can establish directly the se-mantic relatedness of two entities.

Valuing Semantic Relatedness

Traditional search engines based on syntactic search are unable to solve key issues like synonymy and polysemy. Solving these issues leads to the invention of the semantic web. The semantic search engines indeed overcome these issues. Nowadays the most important part of the data remains unstructured documents. It is consequently very time consuming to annotate such big data. Concept based retrieval systems intend to manage directly unstructured documents. Semantic relationships are their main feature to extend syntactic search. In most of the methods implemented so far, concepts are used for both indexing and searching. Words remain the smallest unit to process semantic relatedness. The differences persist in the way that concepts are represented, mapped to each other, and managed for the sake of indexing and/or searching. Our approach is based on Wikipedia concepts. Concepts are represented as an undirected graph. Their semantic relatedness are computed with a distance derived from a semantic similarity measure. The same distance is used to calculate both semantic relatedness and query matching. DOI:   http://dx.doi.org/10.11591/telkomnika.v12i8.5143

/pdf/conceptual-search-based-on-semantic-relatedness-3bihalzmmm.pdf

Conceptual Search Based on Semantic Relatedness

Similarity is a tool widely used in various domains such as DNA sequence analysis, knowledge representation, natural language processing, data mining, information retrieval, and information flow. Computing semantic similarity between two entities is a non-trivial task. There are many ways to define semantic similarity. Some measures have been proposed combining both statistical information and lexical similarity. It is difficult for a measure that performs well in a given domain to be applied with accuracy in another domain. Similarity measure may perform better with one language than another. Word is supposed to be not only similar to itself but also to some of its synonyms in a given context and some words with common roots. Our approach is designed to perform query matching and compute semantic relatedness using word occurrences. It performs better than classical measures like TF-IDF and Cosine. Although it is not a metric, the proposed similarity measure can be used for a wide range of content analysis tasks based on semantic distance and its efficacy has been demonstrated. The measure is not corpus dependent so it can establish directly the semantic relatedness of two entities. DOI:  http://dx.doi.org/10.11591/telkomnika.v12i8.6034

/pdf/valuing-semantic-similarity-4v0xyjp5xn.pdf

Abdoulahi Boubacar

Papers

Concept Based Query Expansion

Valuing Semantic Relatedness

Conceptual Search Based on Semantic Relatedness

Valuing Semantic Similarity