Information Retrieval Process Research Articles

A survey of quantum language models

Language model is a fundamental research topic in areas related to natural language processing. In recent years, researchers have proposed quantum language models based on the probability theory of quantum mechanics. This paper aims to review the research motivation and the current progress of constructing various quantum language models. First, it reviews the research problems of classical language models. Then, it introduces some quantum language models in information retrieval and speech processing, as well as an end-to-end quantum language model based on neural network architecture. By analyzing the advantages and disadvantages of each quantum language model considered here, taking into account the essential connection between quantum mechanics and neural networks, we outline our vision for future research directions.

Recuperación de Información Basada en Técnicas de Minería Web

Actualmente, la recuperación de información en Internet se ha convertido en una tarea compleja debido a varios aspectos relacionados con la enorme cantidad de datos heterogéneos y no estructurados. De hecho, los recursos Web tienen muchas características diferentes que dificultan los procesos de búsqueda. Además, la subjetividad y la incertidumbre, asociadas con las peticiones de los usuarios, dificultan la construcción de consultas eficientes para ser utilizadas en buscadores o navega-dores. En este trabajo se presenta un modelo de minería web para mejorar los procesos de recuperación de información. El modelo propuesto tiene dos componentes principales: el primero es un módulo de análisis de requisitos que ayuda a los usuarios a crear consultas y el segundo componente es un módu-lo de minería Web que utiliza estas consultas para guiar el proceso de búsqueda. Los resultados obteni-dos en las pruebas realizadas demuestran que el modelo recupera información de acuerdo a las defini-das por el usuario de manera adecuada.

Query Expansion Using Conceptual Knowledge in Computer Science

Traditional information retrieval systems retrieve documents based on keyword based matching, thereby incapable to provide results according to user information needs. These systems do not consider the semantic relationships among the user query keywords, thus cannot interpret the query context accurately. Query Expansion technique enhances the performance of information retrieval process by expanding user query with relevant meaningful concepts. Ontology represents semantics of a domain, and emerges as an important resource for query expansion. In this paper, we propose a query expansion framework based on conceptual knowledge derived from ontology in the domain of computer science. The system prototype results show good average precision percentage of 89.2% over keyword based search.

A novel combinatorial merge-split approach for automatic clustering using imperialist competitive algorithm

Cluster analysis has a wide application in many areas, including pattern recognition, information retrieval, and image processing. In most real-world clustering problems, the number of clusters must be predetermined. Automatic clustering is a promising solution for this challenge which automatically determines the number and structure of clusters in data. In recent years, the evolutionary algorithm due to their search mechanisms has been popular in solving automatic clustering problems. Imperialist Competitive Algorithm (ICA) is a successful evolutionary algorithm. In this paper, for the first time, Imperialist Competitive Algorithm (ICA) is used for solving automatic clustering problems, called “the automatic clustering using ICA (AC-ICA)”. In the proposed algorithm, in order to increase the exploration ability, the movement of colonies toward the imperialist was changed at the assimilation step. A new method has been provided for changing the number of clusters by combining random and homogeneity based merge-split approach. Furthermore, an efficient method based on density has been proposed for reinitializing empty cluster centers. To use AC-ICA in automatic clustering, the initialization and imperialist competition steps were changed. Based on changes in these two steps, a framework was provided for changing different types of ICA to solve automatic clustering problems. Then, the basic ICA and its three recently developed types, were changed by this framework and their performances in automatic clustering were compared to AC-ICA. The examinations were done on six synthetic and ten real word data sets. The comparison of the proposed algorithm's results with basic ICA, its three recently developed types and several state-of-art automatic clustering methods, shows AC-ICA's superiority in terms of the speed of convergence to the optimal solution and quality of the obtained solution. We also applied our algorithm to a real world application (i.e., face recognition) and the achieved results were acceptable.

A brief review on text summarization methods

In present scenario, text summarization is a popular and active field of research in both the Information Retrieval (IR) and Natural Language Processing (NLP) communities. Summarization is important for IR since it is a means to identify useful information by condensing the document from large corpus of data in an efficient way. In this study, different aspects of text summarization methods with strength, limitation and gap within the methods are presented.

Report on the 2nd International Workshop on Recent Trends in News Information Retrieval (NewsIR'18)

The news industry has undergone a revolution in the past decade, with substantial changes continuing to this day. News consumption habits are changing due to the increase in the volume of news and the variety of sources. Readers need new mechanisms to cope with this vast volume of information in order to not only find a signal in the noise, but also to understand what is happening in the world given the multiple points of view describing events. These challenges in journalism relate to Information Retrieval (IR) and Natural Language Processing (NLP) fields such as: verification of a source's reliability; the integration of news with other sources of information; real-time processing of both news content and social streams; de-duplication of stories; and entity detection and disambiguation. Although IR and NLP have been applied to news for decades, the changing nature of the space requires fresh approaches and a closer collaboration with our colleagues from the journalism environment. Following the success of the previous version of the workshop (NewsIR'16), the goal of this workshop, held in conjunction with ECIR 2018, is to continue to stimulate such discussion between the communities and to share interesting approaches to solve real user problems. A total number of 19 submissions were received and reviewed, of which 12 were accepted for presentation. In addition to that, we had over 30 registered participants in the workshop who were pleased to attend the two keynote talks given by well-known experts in the field - Edgar Meij (from industry) and Peter Tolmie (from academia) and oral and poster presentations from the accepted papers. The workshop also included a breakout session to discuss ideas for a future data challenge in news IR and closed with a focused panel discussion to reflect on the day. In summary, several ideas were presented in the workshop on solving complex information needs in the news domain. In addition, the workshop concluded with suggestions of important challenges and shared tasks to work on as a community for News IR.

Exploiting named entity recognition for improving syntactic-based web service discovery

Web Services have become essential to the software industry as they represent reusable, remotely accessible functionality and data. Since Web Services must be discovered before being consumed, many discovery approaches applying classic Information Retrieval techniques, which store and process textual service descriptions, have arisen. These efforts are affected by term mismatch: a description relevant to a query can be retrieved only if they share many words. We present an approach to improve Web Service discoverability that automatically augments Web Service descriptions and can be used on top of such existing syntactic-based approaches. We exploit Named Entity Recognition to identify entities in descriptions and expand them with information from public text corpora, for example, Wikidata, mitigating term mismatch since it exploits both synonyms and hypernyms. We evaluated our approach together with classical syntactic-based service discovery approaches using a real 1274-service dataset, achieving up to 15.06% better Recall scores, and up to 17% Precision-at-1, 8% Precision-at-2 and 4% Precision-at-3.

Biomedical literature classification with a CNNs-based hybrid learning network.

Deep learning techniques, e.g., Convolutional Neural Networks (CNNs), have been explosively applied to the research in the fields of information retrieval and natural language processing. However, few research efforts have addressed semantic indexing with deep learning. The use of semantic indexing in the biomedical literature has been limited for several reasons. For instance, MEDLINE citations contain a large number of semantic labels from automatically annotated MeSH terms, and for a great deal of the literature, only the information of the title and the abstract is readily available. In this paper, we propose a Boltzmann Convolutional neural network framework (B-CNN) for biomedicine semantic indexing. In our hybrid learning framework, the CNN can adaptively deal with features of documents that have sequence relationships, and can capture context information accordingly; the Deep Boltzmann Machine (DBM) merges global (the entity in each document) and local information through its training with undirected connections. Additionally, we have designed a hierarchical coarse to fine style indexing structure for learning and classifying documents, and a novel feature extension approach with word sequence embedding and Wikipedia categorization. Comparative experiments were conducted for semantic indexing of biomedical abstract documents; these experiments verified the encouraged performance of our B-CNN model.

A Grey Wolf Optimizer for Text Document Clustering

Abstract Text clustering problem (TCP) is a leading process in many key areas such as information retrieval, text mining, and natural language processing. This presents the need for a potent document clustering algorithm that can be used effectively to navigate, summarize, and arrange information to congregate large data sets. This paper encompasses an adaptation of the grey wolf optimizer (GWO) for TCP, referred to as TCP-GWO. The TCP demands a degree of accuracy beyond that which is possible with metaheuristic swarm-based algorithms. The main issue to be addressed is how to split text documents on the basis of GWO into homogeneous clusters that are sufficiently precise and functional. Specifically, TCP-GWO, or referred to as the document clustering algorithm, used the average distance of documents to the cluster centroid (ADDC) as an objective function to repeatedly optimize the distance between the clusters of the documents. The accuracy and efficiency of the proposed TCP-GWO was demonstrated on a sufficiently large number of documents of variable sizes, documents that were randomly selected from a set of six publicly available data sets. Documents of high complexity were also included in the evaluation process to assess the recall detection rate of the document clustering algorithm. The experimental results for a test set of over a part of 1300 documents showed that failure to correctly cluster a document occurred in less than 20% of cases with a recall rate of more than 65% for a highly complex data set. The high F-measure rate and ability to cluster documents in an effective manner are important advances resulting from this research. The proposed TCP-GWO method was compared to the other well-established text clustering methods using randomly selected data sets. Interestingly, TCP-GWO outperforms the comparative methods in terms of precision, recall, and F-measure rates. In a nutshell, the results illustrate that the proposed TCP-GWO is able to excel compared to the other comparative clustering methods in terms of measurement criteria, whereby more than 55% of the documents were correctly clustered with a high level of accuracy.

A computer‐assisted instructional method based on machine learning in software testing class

AbstractWith the development of computer technology, the old and outdated teaching cases cannot meet requirements on teaching currently. Therefore, in order to solve this problem, we need to rebuild the teaching content and teaching cases. Moreover, in the traditional classroom teaching, each student gets the same practice content, which is not pertinent. In order to solve these two problems, we propose a new method called Software Testing Computer Assistant Education (STCAE), which is based on machine learning, information retrieval, and natural language processing technology. STCAE has three steps: First, STCAE uses NLP to extract the text features from the classified bug reports in the database and to classify all the samples. Second, STCAE scores these bug reports according to the corresponding weight model. Third, STCAE updates the ratings based on the feedbacks of teachers and students on the case. In constructing STCAE, we consider the interactive, creative, pertinent, and error‐correcting capabilities thoroughly in teaching needs, overcoming the four shortcomings of traditional CAI. In addition, we build Software Testing Computer Assistant Education System (STCAES) under STCAE and introduce STCAES into daily teaching. All the achievements in the new course shows that STCAE has achieved great success in practical classroom teaching.

Attributional style of emotions and its relationship with users’ search behaviour

This study aimed to assess the users’ style of attribution of emotions in information retrieval process based on Weiner’s attribution theory of emotion. The research method in the present research is descriptive and the type of study is practical. The population of this study consisted of MA students of different humanistic science branches studying at Imam-Reza International University. A sample of 72 students was selected. The required information were collected through a questionnaire of attribution style and two researcher-made questionnaires. Results showed that the majority of the users attributed their failure and success in information retrieval to internal causes. Also according to Weiner’s theory, they mentioned ‘effort’ as a factor in their success and ‘inability’ and ‘inadequate effort’ as their main failure factors. Research showed that individuals who attribute their emotions to internal factors are more satisfied with their search. On the other hand, it was found that there is a significant relationship between the overall style of user’s attribution and their style of attribution in information retrieval.

An improved Urdu stemming algorithm for text mining based on multi-step hybrid approach

ABSTRACTStemming is the basic operation in Natural language processing (NLP) to remove derivational and inflectional affixes without performing a morphological analysis. This practice is essential to extract the root or stem. In NLP domains, the stemmer is used to improve the process of information retrieval (IR), text classifications (TC), text mining (TM) and related applications. In particular, Urdu stemmers utilize only uni-gram words from the input text by ignoring bigrams, trigrams, and n-gram words. To improve the process and efficiency of stemming, bigrams and trigram words must be included. Despite this fact, there are a few developed methods for Urdu stemmers in the past studies. Therefore, in this paper, we proposed an improved Urdu stemmer, using hybrid approach divided into multi-step operation, to deal with unigram, bigram, and trigram features as well. To evaluate the proposed Urdu stemming method, we have used two corpora; word corpus and text corpus. Moreover, two different evaluation metrics have been applied to measure the performance of the proposed algorithm. The proposed algorithm achieved an accuracy of 92.97% and compression rate of 55%. These experimental results indicate that the proposed system can be used to increase the effectiveness and efficiency of the Urdu stemmer for better information retrieval and text mining applications.

Secure and Efficient Privacy-Preserving Ciphertext Retrieval in Connected Vehicular Cloud Computing

As vehicular equipment is becoming more and more intelligent, the vehicular information service, as the main means of capturing information, has been far from able to meet the needs of occupants [1, 2]. Cloud computing, with its powerful computing and storage capabilities, convenient network access, energy saving and excellent scalability, reliability, availability, and other advantages, can be an effective solution to the limitations of existing automotive information services. Connected vehicular cloud computing, which combines cloud computing and VANETs, has the characteristics of both a cloud platform and a mobile ad hoc network, including autonomy and no fixed structure, good scalability, and so on. However, during the information retrieval, high-density node distribution and high-speed mobile nodes may directly affect the information transmission capacity of a VANET by information tampering, transmission delay, and other issues. In this article, we propose a ciphertext-based search system that exploits RSUs as super peers for connected vehicular cloud computing. The proposed system supports ciphertext retrieval for related documents. In the proposed system, all the computations and retrieval operations are handled by super stationary peers, while documents are stored in the cloud to achieve high efficiency and security of the index structure. We can also reduce the impact of vehicle dynamics on the information retrieval process in this way. In our system, the indexing efficiency is also improved by utilizing a hybrid indexing structure in which binary trees are nested in a B+ tree. Through security analysis and performance evaluation, we demonstrate that our proposal can achieve acceptable security and efficiency.

Understanding Image Impressiveness Inspired by Instantaneous Human Perceptual Cues

With the explosion of visual information nowadays, millions of digital images are available to the users. How to efficiently explore a large set of images and retrieve useful information thus becomes extremely important. Unfortunately only some of the images can impress the user at first glance. Others that make little sense in human perception are often discarded, while still costing valuable time and space. Therefore, it is significant to identify these two kinds of images for relieving the load of online repositories and accelerating information retrieval process. However, most of the existing image properties, e.g., memorability and popularity, are based on repeated human interactions, which limit the research and application of evaluating image quality in terms of instantaneous impression. In this paper, we propose a novel image property, called impressiveness, that measures how images impress people with a short-term contact. This is based on an impression-driven model inspired by a number of important human perceptual cues. To achieve this, we first collect three datasets in various domains, which are labeled according to the instantaneous sensation of the annotators. Then we investigate the impressiveness property via six established human perceptual cues as well as the corresponding features from pixel to semantic levels. Sequentially, we verify the consistency of the impressiveness which can be quantitatively measured by multiple visual representations, and evaluate their latent relationships. Finally, we apply the proposed impressiveness property to rank the images for an efficient image recommendation system.

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.

A SURVEY PAPER ON INFORMATION RETRIEVAL SYSTEM

Information retrieval is the process of obtaining and presenting more related information from the largest collection of information resources according to the user’s need. The tremendous growth in information resources on the Internet makes the information retrieval process a tedious and difficult task for users. Due to information overloading, there is a need for better techniques to retrieve most relevant information from web. This paper presents the information retrieval system by using the PSO algorithm. In presented system, to extract the text from web documents, all html tags are removed. After that stop words and special characters are removed from extracted text for recovering only meaningful contents. TF-IDF concept is used for feature selection. Now PSO optimization technique is used for identifying and refining the features set, these selected features are stored in a database which is used for information retrieval process. In other hand input query is converted into more than one similar semantic query strings. These query strings are compared with the obtained feature sets in the database by using the cosine similarity function. The most similar text is retrieved as an outcome of the information retrieval system.

Abstract P6-11-02: Voice of cancer patients: Analysis of patient concerns regarding scalp cooling devices for prevention of chemotherapy induced alopecia

Abstract Adjuvant chemotherapies for breast cancer cause hair loss in majority of patients. Although Chemo Induced Alopecia (CIA) is temporary, is distressing for many patients and about 7% patients treated with docetaxel experience permanent hair loss. Scalp cooling devices (SCDs) have been shown to reduce hair loss in patients receiving chemo. Many patients share their experiences in online forums as freely shared messages and can be used to analyze concerns regarding CIA and SCDs. We use our automated system, VoCP, to analyze these messages and assess the utilization and efficacy of SCDs, concerns and associated barriers. Method: We collected 15.13 million unique messages (987,189 patients) from 37 cancer forums that provide clinically relevant information; we built custom ontologies for chemo drugs and regimens, hair loss, SCDs, supportive therapy and efficacy. We then used VoCP (using techniques from Artificial Intelligence - deep learning, information retrieval and natural language processing) to extract relevant information. Results: Out of 15.13 million, 17,966 messages from 4,258 patients discussed the use of SCDs during chemo. 16,527 of these were inquiring about SCDs, e.g., do SCDs work, side effects, Difficulty in use, risk of scalp and brain metastasis, cost and insurance coverage, ease of obtaining and manufacturers. 2,213 messages from 817 patients discussed SCDs with Docetaxel, 1,470 from 687 patients discussed with FEC/AC, and 517 from 249 patients discussed with AC/Taxol. In 1,439 messages, 668 distinct patients who used SCDs mentioned that, they were able to keep 50-75% of their hair but experienced significant hair-thinning. Most users were satisfied with SCDs' use and would prefer them over loosing hair completely; comments regarding side effects, barriers and advice included: · Headaches, shivering, frost-bite, heaviness, neck and shoulder discomfort, chills, brain freeze, scalp pain, migraine, drowsiness, dizziness and cold; May use Lorazepam, Ibuprofen and Acetaminophen. · Use mittens/hand-gloves, scarves, blankets and heating pads to keep body warm and avoid shivering · Use cold caps during and 3-5 hours after chemo; change them every 15-30 minutes · Cold caps with varying temperatures - warmer in front and sides for ear and forehead protection – may help; trim long hair · For cold caps, either the facility needs to provide a freezer or patients need to bring their own · Penguin cold caps are most common (2,055 messages) but monthly rent is $500-$600 · Patients can buy Elastogel caps (918 messages) for about $100 · Alternatives include icepacks/wrap-arounds provided by companies such as ElastoGel · For single cap cooling devices such as DigniCap (337 messages) and Paxman (434), facility has to provide the system · Rapunzel Project (171 messages) can help with scalp cooling gear, freezers and counseling; 79 SCD users mentioned getting their help Discussion: Despite significant discomfort, cost and inconvenience, many patients are satisfied with SCDs' use for CIA. More programs like Rapunzel project are needed to help patients. By analyzing millions of messages, VoCP provides meaningful insights into patients' treatment and concerns and gives insight into unmet needs for further research and resources. Citation Format: Aggarwal S, Sharma R, Sharma R, Aggarwal A. Voice of cancer patients: Analysis of patient concerns regarding scalp cooling devices for prevention of chemotherapy induced alopecia [abstract]. In: Proceedings of the 2017 San Antonio Breast Cancer Symposium; 2017 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2018;78(4 Suppl):Abstract nr P6-11-02.

Rule based Text Extraction from a Bibliographic Database

<p>The emergent concept of ‘ Big Data’ has shifted the paradigm from information retrieval to information extraction techniques. The information extraction techniques enables corpus analysis to draw useful interpretations and its possible applications. Selection of appropriate information extraction technique depends upon the type of data being dealt with and its possible applications. In an R&D environment, the published information is considered as an authenticated benchmark to study and analyse the growth pattern in that field of science, medicine, business. A rule based information extraction process, on the selected data extracted from a bibliographic database of published R&D papers is proposed in this paper. Aim of the study is to build up a database on relevant concepts, cleaning of retrieved data and automate the process of information retrieval in the local database. For this purpose, a concept based ‘subject profiles’ in the area of advanced semiconductors as well as the rules for text extraction from metadata retrieved from the bibliographic database was developed. This subset was used as an input to the knowledge domain to support R&D in the area of ‘advanced semiconductor materials and devices’ and provide information services on Intranet. Study found that concept based pattern matching on the datasets downloaded yielded better results as compared to the results by using the controlled vocabulary of the source database .</p>

Ontological Optimization for Latent Semantic Indexing of Arabic Corpus

The dimensionality reduction is a critical problem in the information retrieval process. The higher dimensions directly affect the search performance in terms of Recall and Precision. The dimensionality reduction enabling the search to be semantically based instead of lexically based as the dimensions are defined in terms of the semantic concepts instead of traditional terms or keywords. Latent Semantic Indexing (LSI) is a mathematical extension of the classical Vector Space Model (VSM). LSI is used to discover the latent semantic in the search space by extracting concepts from the original terms in the space. LSI is based on the Singular Value Decomposition (SVD) to reduce the dimension of the term space into a lower dimensional LSI space. In this paper, we propose a methodology for extra optimal LSI dimension reduction via two reduction levels. The first reduction level is based on an ontological conceptualization process. The Universal Wordnet ontology (UWN) is used to develop an ontological based concept space instead of the term space. As a second reduction level, the SVD is applied to the extracted concept space for getting an optimal LSI conceptualization. The experimental results of this research indicate an improvement in the search results in terms of both Precision and Recall as the proposed methodology addresses the Synonymy and Polysemy problems effectively.

Classifying Provider-EHR Screen Interactions During ICU Pre-Rounds.

Electronic health records (EHR) usability is paramount for high quality of care delivery, clinician productivity and effectiveness, and patient outcomes. This paper investigates clinicians EHR pathways during pre-rounds by characterizing the top EHR screens, duration per screen, and the path taken to complete a task. Structured observations were conducted of ICU providers interacting with the EHR in a real-time, real-world setting to better characterize the information retrieval process. Based on preliminary results of the observations, key areas of information needs have been identified and a preliminary model of EHR workflow has been established. The study highlights that there is a clear discrepancy in usage in EHR screens among ICU residents suggesting that there is a perceived clinician's pathology to finding patient information.