Information Retrieval Approach Research Articles

Learning, Probability and Logic: Toward a Unified Approach for Content-Based Music Information Retrieval

Within the last fifteen years, the field of Music Information Retrieval (MIR) has made tremendous progress in the development of algorithms for organizing and analyzing the ever-increasing large and varied amount of music and music-related data available digitally. However, the development of content-based methods to enable or improve multimedia retrieval still remains a central challenge. In this perspective paper, we critically look at the problem of automatic chord estimation from audio recordings as a case study of content-based algorithms, and point out several bottlenecks in current approaches: expressiveness and flexibility are obtained to the expense of robustness and vice-versa; available multimodal sources of information are little exploited; modeling multi-faceted and strongly interrelated musical information is limited with current architectures; models are typically restricted to short-term analysis that does not account for the hierarchical temporal structure of musical signals. Dealing with music data requires the ability to handle both uncertainty and complex relational structure at multiple levels of representation. Traditional approaches have generally treated these two aspects separately, probability and learning being the standard way to represent uncertainty in knowledge, while logical representation being the standard way to represent knowledge and complex relational information. We advocate that the identified hurdles of current approaches could be overcome by recent developments in the area of Statistical Relational Artificial Intelligence (StarAI) that unifies probability, logic and (deep) learning. We show that existing approaches used in MIR find powerful extensions and unifications in StarAI, and we explain why we think it is time to consider the new perspectives offered by this promising research field.

The state-of-the-art in expert recommendation systems

The recent rapid growth of the Internet content has led to building recommendation systems that guide users to their needs through an information retrieving process. An expert recommendation system is an emerging area that attempts to detect the most knowledgeable people in some specific topics. This detection is based on both the extracted information from peoples’ activities and the content of the documents concerned with them. Moreover, an expert recommendation system takes a user topic or query and then provides a list of people sorted by the degree of their relevant expertise with the given topic or query. These systems can be modeled by information retrieval approaches, along with search engines or a combination of natural language processing systems. The following study provides a critical overview of existing expert recommendation systems and their advantages and disadvantages, considering as well different techniques employed by them.

A learning to rank approach for cross-language information retrieval exploiting multiple translation resources

AbstractCross-language information retrieval (CLIR), finding information in one language in response to queries expressed in another language, has attracted much attention due to the explosive growth of multilingual information in the World Wide Web. One important issue in CLIR is how to apply monolingual information retrieval (IR) methods in cross-lingual environments. Recently, learning to rank (LTR) approach has been successfully employed in different IR tasks. In this paper, we use LTR for CLIR. In order to adapt monolingual LTR techniques in CLIR and pass the barrier of language difference, we map monolingual IR features to CLIR ones using translation information extracted from different translation resources. The performance of CLIR is highly dependent on the size and quality of available bilingual resources. Effective use of available resources is especially important in low-resource language pairs. In this paper, we further propose an LTR-based method for combining translation resources in CLIR. We have studied the effectiveness of the proposed approach using different translation resources. Our results also show that LTR can be used to successfully combine different translation resources to improve the CLIR performance. In the best scenario, the LTR-based combination method improves the performance of single-resource-based CLIR method by 6% in terms of Mean Average Precision.

Report on the 3rd Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2018)

The 3rd joint BIRNDL workshop was held at the 41st ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2018) in Ann Arbor, USA. BIRNDL 2018 intended to stimulate IR researchers and digital library professionals to elaborate on new approaches in natural language processing, information retrieval, scientometrics, and recommendation techniques that can advance the state-of-the-art in scholarly document understanding, analysis, and retrieval at scale. The workshop incorporated three paper sessions and the 4th edition of the CL-SciSumm Shared Task.

Effective Big Data Retrieval Using Deep Learning Modified Neural Networks

In big data, the information retrieval (IR) embraces the discovery of documents from a compilation of dataset which are related to the user query. Usually, the data retrieval systems are used to scan the data. The existent approaches that employ customary IR are wearisome for big document collections. Recently, IR approaches were developed, albeit these are faster comparing to the traditional method but the quality of the document retrieved is less. To overcome such difficulties, here, effectual big data retrieval utilizing Deep Learning Modified Neural Networks (DLMNN) is proposed. Initially, the general pre-processing along with feature extraction steps are taken place. In preprocessing stage, unwanted data are removed and also used for changing the unstructured data in to structured data then in FE is done using frequency and entropy calculation of the given input data. Secondly, find the closed recurrent item dataset, after that find the weight of provided data using entropy measure and frequent item measure. In the 3rd step, the documents are clustered utilizing the k-means algorithm and then classified using DLMNN. The K-Means algorithm is utilized to partition the collection of documents into several clusters then the DLMNN is used for classifying the documents into positive and negative classes. The proposed DLNN weight parameters are optimized utilizing the cuckoo search (CS) optimization algorithm. The last stage on the training process section is generating a training data-base. In the other part, the retrieval process is performed, in this section it pre-processes the user query and discovers the frequency item set then gets retrieval data. Finally, check the similarity assessment, if the information is found then it is visualized, otherwise the document is returned to the initial position. Experimental results contrasted with the previous MRT and IRI-RAS techniques concerning precision, recall, F-measure along with computation time. The proposed document IR is better when comparing with existent methods.

Deep Learning With Customized Abstract Syntax Tree for Bug Localization

Given a bug report, bug localization technique can help developers automatically locate potential buggy files. Information retrieval and deep learning approaches have been applied in bug localization by extracting lexical features in bug reports and syntactic features in source code files, though they fail to utilize the structural and semantic information of source code files. In this paper, we present a bug localization system CAST, which exploits deep learning and customized abstract syntax trees of programs to locate potential buggy source files automatically and effectively. Specifically, CAST extracts both lexical semantics in bug reports (e.g., words) and source files (e.g., method names) and program semantics in source files (e.g., abstract syntax tree, AST). Moreover, CAST enhances the tree-based convolutional neural network (TBCNN) model with customized ASTs, which distinguish between user-defined methods and system-provided ones to reflect their contributions leading to defects. Furthermore, customized ASTs group the syntactic entities with similar semantics and prune the ones with little or redundant semantics in order to facilitate the learning performance. Experimental results on four widely-used software projects show that CAST significantly outperforms the state-of-the-art methods in locating the buggy source files.

The Use of Ontology in Retrieval: A Study on Textual, Multilingual, and Multimedia Retrieval

Web contains a vast amount of data, which are accumulated, studied, and utilized by a huge number of users on a daily basis. A substantial amount of data on the Web is available in an unstructured format, such as Web pages, books, journals, and files. Acquiring appropriate information from such humongous data has become quite challenging and a time-consuming task. Trivial keyword-based information retrieval systems highly depend on the statistics of data, thus facing word mismatch problem due to inevitable semantic and context variations of a certain word. Therefore, this marks the desperate need to organize such massive data into a structured format so that information can be easily processed in a large context by taking data semantics into account. Ontologies are not only being extensively employed in the semantic Web to store unstructured information in an organized and structured way but it has also raised the performance of diverse information retrieval approaches to a great extent. Ontological information retrieval systems retrieve data based on the similarity of semantics between the user query and the indexed data. This paper reviews modern ontology-based information retrieval methods for textual, multimedia, and cross-lingual data types. Furthermore, we compare and categorize the most recent approaches used in the above-mentioned information retrieval methods along with their major drawbacks and advantages.

An Enhanced Concept based Approach for User Centered Health Information Retrieval to Address Presentation Issues

The diversity of health information seekers signifies the enormous variety of information needs by numerous users. The existing health information retrieval systems failed to address the information needs of both medical expert and laymen patients. This study focused on designing an enhanced information retrieval approach using the concept based approach that would address the information needs of both medical experts and laymen patients. We evaluated and compared the performance of the proposed enhanced concept based approach with the existing approaches namely: concept based approach (CBA), query likelihood model (QLM) and latent semantic indexing (LSI) approach using Diagnosia 7, Medical Subject Heading (MeSH), Khresmoi Project 6 and Genetic Home Reference datasets. The experimental results obtained shows that the proposed enhanced concept based approach manage to score similarity scores of 1.0 (100%) in respect to maxSim values for all the runs in all the four datasets and idf weighting values of between 3.82 – 3.86 for all the runs in all the four datasets. While the existing approaches (CBA, QLM, LSI) scored the maxSim scores of 0.5 (50%) for all their runs in all the four dataset and idf weighting values of between 1.40 – 1.47 for all the four dataset, as a result of their inability to generate and display medical search results in both medical experts and layman’s forms. These results shows that the proposed enhanced concept based approach is the best approach suited to be used in addressing presentation issues.

MOSSA: a morpho-semantic knowledge extraction system for Arabic information retrieval

In this paper, we propose to exploit different morpho-semantic resources to enhance Arabic information retrieval (IR). We use standardised LMF Arabic dictionaries and Arabic corpora. Our goal by this communication is to take advantage of the different existing resources to extract useful knowledge for Arabic IR. We equally study the impact of the Arabic morphology on IR effectiveness. Several query expansion strategies are carried based on morphological, semantic and morpho-semantic relations. In addition, combining such knowledge is also studied and evaluated. We experiment the effect of short diacritics and part of speech (POS) disambiguation and tagging in the indexing step. A graph-based representation is used to formalise knowledge resources graph-based representation. This latter represents a powerful formalism to express semantics of texts and to support NLP tools and applications as IR. Several experimental comparisons are handled between the different used knowledge resources and the different carried IR approaches.

MOSSA: a morpho-semantic knowledge extraction system for Arabic information retrieval

In this paper, we propose to exploit different morpho-semantic resources to enhance Arabic information retrieval (IR). We use standardised LMF Arabic dictionaries and Arabic corpora. Our goal by this communication is to take advantage of the different existing resources to extract useful knowledge for Arabic IR. We equally study the impact of the Arabic morphology on IR effectiveness. Several query expansion strategies are carried based on morphological, semantic and morpho-semantic relations. In addition, combining such knowledge is also studied and evaluated. We experiment the effect of short diacritics and part of speech (POS) disambiguation and tagging in the indexing step. A graph-based representation is used to formalise knowledge resources graph-based representation. This latter represents a powerful formalism to express semantics of texts and to support NLP tools and applications as IR. Several experimental comparisons are handled between the different used knowledge resources and the different carried IR approaches.

Integration of User Profile in Search Process according to the Bayesian Approach

Most information retrieval system (IRS) rely on the so called system-centred approach,<br /> behaves as a black box, which produces the same answer to the same query, independently on the<br /> user’s specific information needs. Without considering the user, it is hard to know which sense<br /> refers to in a query. To satisfy user needs, personalization is an appropriate solution to improve the<br /> IRS usability. Modeling the user profile can be the first step towards personalization of information<br /> search. The user profile refers to his/her interests built across his/her interactions with the retrieval<br /> system. In this paper, we present a personalized information retrieval approach for building and<br /> exploiting the user profile in search process, based on Bayesian network. The theoretical<br /> framework provided by these networks allows better capturing the relationships between different<br /> information. Experiments carried out on TREC-1 ad hoc and TREC 2011 Track collections show<br /> that our approach achieves significant improvements over a personalized search approach described<br /> in the state of the art and also to a baseline search information process that do not consider the user<br /> profile

Full-Band Signal Extraction From Sensors in Extreme Environments: The NASA InSight Microseismometer

Physically meaningful signal extraction from sensors deployed in extreme environments requires a combination of attenuation of confounding inputs and the removal of their residual using decorrelation techniques. In space applications where the resources for physical attenuation are limited, there is a necessity to apply the most effective post-processing analysis available. This paper describes the extraction of the seismic signal from an MEMS microseismometer to be deployed on the surface of Mars. The signal processing, which covers the full bandwidth $1 \times 10^{-5}$ Hz to 40 Hz, uses a novel application of sensor fusion through an indirect Kalman Filter in combination with a thermal model of the microseismometer to remove the aseismic contribution of temperature over the frequency range. Owing to the full-band decorrelation, the analysis (based on pre-landing testing in analogous scenarios) produces both a characterization of the microseismomter and a signal processing approach for information retrieval on Mars, along with other planetary and terrestrial planetary deployments.

An efficient approach for land record classification and information retrieval in data warehouse

Data warehouse collects recent and old land record data used to generate analytical reports. Depending on factors such as historical evolution and local traditions, the system of land records differs from states. The survey maps, textual data, and registration records are matched with each other and updated for the registration and maintenance of such land records. In addition, citizens must get access to multiple agencies to get full information on land records. In order to eliminate such limitation, we propose a novel Artificial Neural Network (ANN)–FUZZY–cat swarm optimization (CSO) approach to accurately predict and retrieve the information. First, the ANN classifies the input data for ordering the information to construct a database of different classes. Then, the mongo database store a large amount of land record data for facilitating easy maintenance, prompt updating of land records and security. The accurate results for the user query are retrieved using CSO algorithm. Optimal rules allow users to access their posts easily. Finally, better performance results are for the information retrieval in terms of accuracy, precision, and recall.

AN INFORMATION RETRIEVAL APPROACH FOR ASSISTING USERS IN SOFTWARE ENGINEERING PROCESSES

Documents written in natural language constitute a major part of the artifacts produced during the software engineering life cycle. There is a growing interest in creating tools that can assist users in all phases of the software life cycle. The assistance requires techniques that go beyond traditional static and dynamic analysis. An example of such a technique is the application of information retrieval (IR), which exploits information found in documents of a software engineering process. The increased availability of data created as part of the software development process allows managers to apply novel analysis techniques on the data and use the results to guide the project's stakeholders. These data are then used to predict defects, gather insight into a project's life-cycle, and other tasks. This work proposes an IR approach to assist users in software engineering processes according their profile. The approach consists in recommending them related documents to a retrieved one in order to users understand and follow the process in a correct way. Furthermore, the assistance concentrates on legacy systems in which engineers must acquire knowledge generated by others. Implementation of the approach and an overview of evaluation are also summarized.

Information retrieval in physical geography

Information retrieval (IR) methods seek to locate meaningful documents in large collections of textual and other data. Few studies apply these techniques to discover descriptions in historical documents for physical geography applications. This absence is noteworthy given the use of qualitative historical descriptions in physical geography and the amount of historical documentation online. This study, therefore, introduces an IR approach for finding meaningful and geographically resolved historical descriptions in large digital collections of historical documents. Presenting a biogeography application, it develops a ‘search engine’ using a boosted regression trees (BRT) model to assist in finding forest compositional descriptions (FCDs) based on textual features in a collection of county histories. The study then investigates whether FCDs corroborate existing estimates of relative abundances and spatial distributions of tree taxa from presettlement land survey records (PLSRs) and existing range maps. The BRT model is trained using portions of text from 458 US county histories. Evaluating the model’s performance upon a spatially independent test dataset, the model helps discover 97.5% of FCDs while reducing the amount of text to search through to 0.3% of total. The prevalence rank of taxa in FCDs (i.e. the number of times a taxon is mentioned at least once in an FCD, divided by the total number of FCDs, then ranked) is strongly related to the abundance rank in PLSRs. Patterns in species mentions from FCDs generally match relative abundance patterns from PLSRs. However, analyses suggest that FCDs contain biases towards large and economically valuable tree taxa and against smaller taxa. In the end, the study demonstrates the potential of IR approaches for developing novel datasets over large geographic areas, corroborating existing historical datasets, and providing spatial coverage of historic phenomena.

Fast and effective cluster-based information retrieval using frequent closed itemsets

Document Information retrieval consists of finding the documents in a collection of documents that are the most relevant to a user query. Information retrieval techniques are widely-used by organizations to facilitate the search for information. However, applying traditional information retrieval techniques is time consuming for large document collections. Recently, cluster-based information retrieval approaches have been developed. Although these approaches are often much faster than traditional approaches for processing large document collections, the quality of the documents retrieved by cluster-based approaches is often less than that of traditional approaches. To address this drawback of cluster-based approaches, and improve the performance of information retrieval both in terms of runtime and quality of retrieved documents, this paper proposes a new cluster-based information retrieval approach named ICIR (Intelligent Cluster-based Information Retrieval). The proposed approach combines k-means clustering with frequent closed itemset mining to extract clusters of documents and find frequent terms in each cluster. Patterns discovered in each cluster are then used to select the most relevant document clusters to answer each user query. Four alternative heuristics are proposed to select the most relevant clusters, and two alternative heuristics for choosing documents in the selected clusters. Thus, eight versions of the proposed approach are obtained. To validate the proposed approach, extensive experiments have been carried out on well-known document collections. Results show that the designed approach outperforms traditional and cluster-based information retrieval approaches both in terms of execution time and quality of the returned documents.

Machine translation-based bug localization technique for bridging lexical gap

ContextThe challenge of locating bugs in mostly large-scale software systems has led to the development of bug localization techniques. However, the lexical mismatch between bug reports and source codes degrades the performances of existing information retrieval or machine learning-based approaches. ObjectiveTo bridge the lexical gap and improve the effectiveness of localizing buggy files by leveraging the extracted semantic information from bug reports and source code. MethodWe present BugTranslator, a novel deep learning-based machine translation technique composed of an attention-based recurrent neural network (RNN) Encoder-Decoder with long short-term memory cells. One RNN encodes bug reports into several context vectors that are decoded by another RNN into code tokens of buggy files. The technique studies and adopts the relevance between the extracted semantic information from bug reports and source files. ResultsThe experimental results show that BugTranslator outperforms a current state-of-the-art word embedding technique on three open-source projects with higher MAP and MRR. The results show that BugTranslator can rank actual buggy files at the second or third places on average. ConclusionBugTranslator distinguishes bug reports and source code into different symbolic classes and then extracts deep semantic similarity and relevance between bug reports and the corresponding buggy files to bridge the lexical gap at its source, thereby further improving the performance of bug localization.

Bi-Gram Term Collocations-based Query Expansion Approach for Improving Arabic Information Retrieval

In the era of information overloading, information retrieval systems are vital applications. Many researchers try to enhance the search results by introducing new methods. Unlike the English language, some languages like Arabic have complex morphological aspects and lack both linguistic and semantic resources. This paper proposes a language-independent semantic-based information retrieval approach, which expands the user query using bi-gram term collocations. The proposed approach has two main contributions. First, the bi-gram term collocations employed to expand the user query are automatically mined from the text corpus, therefore there is no need for an external semantic resource. Second, due to the complexity of the language morphology, the system index is constructed using the corpus words to save the cost and effort of the stemming process. A system prototype for the Arabic language was implemented and evaluated versus the stem-based method. The experimental evaluation has been conducted on the scripts of the Arabic Holy Quran. The evaluation results demonstrate that the proposed system outperforms the stem-based method in terms of precision and recall.

Report on the 2nd Joint Workshop on Bibliometric-enhanced Information Retrieval and Natural Language Processing for Digital Libraries (BIRNDL 2017)

The large scale of scholarly publications poses a challenge for scholars in information seeking and sense-making. Bibliometrics, information retrieval (IR), text mining, and NLP techniques could help in these activities, but are not yet widely implemented in digital libraries. The 2nd joint BIRNDL workshop was held at the 40th ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2017) in Tokyo, Japan. BIRNDL 2017 intended to stimulate IR researchers and digital library professionals to elaborate on new approaches in natural language processing, information retrieval, scientometric, and recommendation techniques that can advance the state-of-the-art in scholarly document understanding, analysis, and retrieval at scale. The workshop incorporated three paper sessions and the 3rd edition of the CL-SciSumm Shared Task.

Information retrieval for systematic reviews in food and feed topics: A narrative review

Systematic review methods are now being used for reviews of food production, food safety and security, plant health, and animal health and welfare. Information retrieval methods in this context have been informed by human health-care approaches and ideally should be based on relevant research and experience. This narrative review seeks to identify and summarize current research-based evidence and experience on information retrieval for systematic reviews in food and feed topics. MEDLINE (Ovid), Science Citation Index (Web of Science), and ScienceDirect (http://www.sciencedirect.com/) were searched in 2012 and 2016. We also contacted topic experts and undertook citation searches. We selected and summarized studies reporting research on information retrieval, as well as published guidance and experience. There is little published evidence on the most efficient way to conduct searches for food and feed topics. There are few available study design search filters, and their use may be problematic given poor or inconsistent reporting of study methods. Food and feed research makes use of a wide range of study designs so it might be best to focus strategy development on capturing study populations, although this also has challenges. There is limited guidance on which resources should be searched and whether publication bias in disciplines relevant to food and feed necessitates extensive searching of the gray literature. There is some limited evidence on information retrieval approaches, but more research is required to inform effective and efficient approaches to searching to populate food and feed reviews.