Information Retrieval Techniques Research Articles

Biomedical Information Retrieval with Positive-Unlabeled Learning and Knowledge Graphs

The rapid growth of biomedical publications has presented significant challenges in the field of information retrieval. Most existing work focuses on document retrieval given explicit queries. However, in real applications such as curated biomedical database maintenance, explicit queries are missing. In this paper, we propose a two-step model for biomedical information retrieval in the case that only a small set of example documents is available without explicit queries. Initially, we extract keywords from the observed documents using large pre-trained language models and biomedical knowledge graphs. These keywords are then enriched with domain-specific entities. Information retrieval techniques can subsequently use the collected entities to rank the documents. Following this, we introduce an iterative Positive-Unlabeled learning method to classify all unlabeled documents. Experiments conducted on the PubMed dataset demonstrate that the proposed technique outperforms the state-of-the-art positive-unlabeled learning methods. The results underscore the effectiveness of integrating large language models and biomedical knowledge graphs in improving zero-shot information retrieval performance in the biomedical domain.

Enhancing integration testing efficiency through AI-driven combined structural and textual class coupling metric

Integration testing, a critical and resource-intensive phase in the software development lifecycle, can account for up to a high percentage of the total testing cost. Identifying classes with high coupling is crucial for efficient integration testing, as these classes are more susceptible to the impact of maintenance-related changes. This research introduces a novel metric called <i>combined structural and textual class coupling</i> (CSTCC), which harnesses the power of artificial intelligence (AI) techniques to predict and rank the most critical classes in an object-oriented software system. CSTCC integrates structural coupling metrics with <i>latent semantic indexing</i> (LSI)-based textual coupling, providing a comprehensive measure of class coupling. LSI, an information retrieval technique, analyses the semantic relationships between classes based on their textual content, enabling CSTCC to capture both structural and conceptual dependencies, resulting in a more accurate identification of high-risk classes. The effectiveness of the proposed approach is rigorously evaluated using mutation testing on four Java open-source projects, and the results demonstrate that test cases developed based on CSTCC achieve high mutation scores, indicating their ability to detect a significant percentage of integration faults. By focusing testing efforts on high-coupling classes identified by CSTCC, developers can potentially save time and cost during integration testing. The results demonstrate that test cases developed based on CSTCC achieve high mutation scores, ranging from 98% to 100%, indicating their ability to detect a significant percentage of integration faults. Additionally, the approach results in substantial efficiency gains, with a notable reduction in the number of test cases needed, saving up to 33.3% of the testing effort in some cases. By focusing testing efforts on high-coupling classes identified by CSTCC, developers can potentially save time and cost during integration testing. The CSTCC metric provides a novel and effective approach to prioritize testing resources and improve the efficiency of integration testing in object-oriented software systems.

CPEQA: A Large Language Model Based Knowledge Base Retrieval System for Chinese Confidentiality Knowledge Question Answering

Large language models (LLMs) have exhibited remarkable performance on various natural language processing (NLP) tasks, particularly in the construction of the intelligent question-answering system. These systems, especially in specialized fields, usually rely on NLP through the retrieval of corpus and answering databases to efficiently provide accurate and concise answers. This paper focuses on the national confidentiality publicity and education field, aiming to address the dilemma of inaccurate knowledge retrieval in this field. Therefore, we design an intelligent confidentiality question-answering system CPEQA by comprehensively utilizing the LLMs platform and information retrieval technique. CPEQA is capable of providing professional answers to questions about Chinese confidentiality publicity and education raised by users. Additionally, we also integrate the conventional database retrieval technique and LLMs into the database query construction, enabling CPEQA to perform real-time queries and data analysis for both single-table and multi-table querying tasks. Through extensive experiments with generated query sentences, we show both methodological comparisons and empirical evaluations of CPEQA’s performance. Experimental results indicate that CPEQA has achieved competitive results on answering precision, recall rate and other metrics. Finally, we explore the challenges of the CPEQA system associated with these techniques and outline potential avenues for future research in this emerging field.

QuAC: Quick Attribute-Centric Type Inference for Python

Python’s dynamic typing facilitates rapid prototyping and underlies its popularity in many domains. However, dynamic typing reduces the power of many static checking and bug-finding tools. Python type annotations can make these tools more useful. Type inference tools aim to reduce developers’ burden of adding them. However, existing type inference tools struggle to support dynamic features, infer correct types (especially container type parameters and non-builtin types), and run in reasonable time. Inspired by Python’s duck typing, where the attributes accessed on Python expressions characterize their implicit interfaces, we propose QuAC (Quick Attribute-Centric Type Inference for Python). At its core, QuAC collects attribute sets for Python expressions and leverages information retrieval techniques to predict classes from these attribute sets. It also recursively predicts container type parameters. We evaluate QuAC’s performance on popular Python projects. Compared to state-of-the-art non-LLM baselines, QuAC predicts types with high accuracy complementary to those predicted by the baselines while not sacrificing coverage. It also demonstrates clear advantages in predicting container type parameters and non-builtin types and reduces run times. Furthermore, QuAC is nearly two orders of magnitude faster than an LLM-based method while covering nearly half of its errorless non-trivial type predictions. It is also significantly more consistent at predicting container type parameters and non-builtin types than the LLM-based method, regardless of whether the project has ground-truth type annotations.

An Intelligent Multi-Agent System using XML for Adaptive Employment Agency Management

In recent years, e-commerce has become a significant social and cultural phenomenon. Many organizations now offer their services online. Within this context, online recruitment services play an important role in supporting individuals in job searches and assisting companies in finding personnel. Conversely, the potential that AI forecasting systems offer in distinct application fields is well known using increasingly high-performance algorithms that are particularly promising and certainly used successfully in job searches. In this field, in general, companies insert their job offers (job proposals) into a database; individuals are supported in their search for a job offer using a search engine based on classic Information Retrieval (IR) techniques. Regarding this, it is presumable that the Information Retrieval techniques currently used by recruitment services, which do not involve the use of rich user profiles, can provide a single individual with a large number of job offers, many of which are of little interest for him. This result could cause strong dissatisfaction for the user, and his renunciation of the use of such services. The Geomatics Laboratory, in the context of forecasting studies in the territorial and environmental fields, is experimenting with forecasting systems also in the business and economics fields to create a customized search engine, proposing a Recommender System developed using intelligent agents and based on XML. This system leverages detailed user profiles to assist users in personalized job offer searches, which combines classic Information Retrieval techniques with User Modeling techniques and artificial intelligence techniques. As a result, in generic domains, our system quickly achieves satisfactory results; however, it struggles to maintain this performance after many sessions. Conversely, in specialized domains, while our system requires many sessions to reach satisfactory performance initially, it consistently delivers outstanding performance once this phase is complete.

Explainable eBook recommendation for extensive reading in K-12 EFL learning

An automatic recommendation system for learning materials in e-learning addresses the challenge of selecting appropriate materials amid information overload and varying self-directed learning (SDL) skills. Such systems can enhance learning by providing personalized recommendations. In Extensive Reading (ER) for English as a Foreign Language (EFL), recommending materials is crucial due to the paradox that learners with low SDL skills struggle to select suitable ER resources, despite ER’s potential to improve SDL. Additionally, determining the difficulty level of ER materials and assessing learners’ progress remains challenging. The system must also explain its recommendations to foster motivation and trust. This study proposes a mechanism to estimate the difficulty of ER materials, adapted to learner preferences, using information retrieval techniques, and an explainable recommendation system for English materials. An experiment was conducted with 240 Japanese junior high school students in an ER program to assess the accuracy of difficulty estimation and identify learner characteristics receptive to the recommendations. While the recommendations did not significantly impact learners’ English skills or motivation, they were positively received. A strong relationship was found between the use and acceptance of recommendations and learners’ motivation. The study suggests that although the system did not increase overall motivation, it has potential to further enhance the motivation of naturally motivated learners.

An empirical study on the state-of-the-art methods for requirement-to-code traceability link recovery

Requirements-to-code traceability link recovery (RC-TLR) can establish connections between requirements and target code artifacts, which is critical for the maintenance and evolution of large software systems. However, to the best of our knowledge, there is no existing experimental study focused on state-of-the-art (SOTA) methods for the RC-TLR problem, and there is also a lack of uniform benchmarks for evaluating new methods in the field. We developed a framework to identify SOTA methods using the Systematic Literature Review method and applied it to research in the RC-TLR field from 2018 to 2023. Through experiments replication on 13 datasets using 6 methods, we observed that for information retrieval-based methods, Close Relations between Target artifacts-based method (CRT), TraceAbility Recovery by Consensual biTerms (TAROT), and Fine-grained TLR (FTLR) performed well on COEST dataset, while Combining Part-Of-Speech with information-retrieval techniques (Conpos) and TAROT achieve promising results in large datasets. As concerns machine learning-based methods, Random Forest consistently exhibits strong performances on all datasets. We hope that this study can provide a comparative benchmark for performance evaluation in the RC-TLR field. The resource repository that we have established is expected to alleviate the workload of researchers in performance analysis, and promote progress of the field.

Ensemble-based Disease Outbreak Detection: Comparative Analysis of Health News Information Retrieval Techniques

Ensemble-based Disease Outbreak Detection: Comparative Analysis of Health News Information Retrieval Techniques

Ensemble-based Disease Outbreak Detection: Comparative Analysis of Health News Information Retrieval Techniques

In India, Kerala is the first state to report a COVID-19 infection case, in January 2020, in a medical student, who returned from Wuhan, China. More recently, in June 2022, Kerala also reported India's first case of monkeypox disease. News websites often publish articles dedicated to reporting disease occurrences and live updates of outbreaks. Through the utilization of data gathered from online digital resources, early detection of outbreaks is possible, and this potential is already identified by the research community. As webpages give a comprehensive collection of reports covering a wide range of themes through hyperlinks, precisely categorizing news articles based on their headlines and retrieving health news is a tedious operation. Hence, this paper proposes a novel and efficient news retrieval technique grounded on an ML-based classification method with an ensemble learning approach to identify reports of disease occurrences from web pages by focusing specifically on the health context of Kerala and a comparison with baseline methods for information retrieval such as keyword-based, phrase-based, and content-based latent semantic analysis method is made.

Enhancing Suggestion Detection in Online User Reviews through Integrated Information Retrieval and Deep Learning Approaches

In the aftermath of the COVID-19 pandemic, using web platforms as a communication medium and decision-making tool in online commerce has become widely acknowledged. User-generated comments, reflecting positive and negative sentiments towards specific items, serve as invaluable indicators, offering recommendations for product and organizational improvements. Consequently, the extraction of suggestions from mined opinions can enhance the efficacy of companies and organizations in this domain. Prevailing research in suggestion mining predominantly employs rule-based methodologies and statistical classifiers, relying on manually identified features. However, a recent trend has emerged wherein researchers explore solutions grounded in deep learning tools and techniques. This study aims to employ information retrieval techniques for the automated identification of suggestions. To this end, various methodologies, including distance measurement approaches, multilayer perceptron neural networks, support vector machines, regression logistics, convolutional neural networks utilizing TF-IDF, Bag of Words (BOW), and Word2Vec vectors, along with keyword extraction, have been integrated. The proposed approach is assessed using the SemEval2019 dataset to extract suggestions from the textual content of online user reviews. The obtained results demonstrate a notable enhancement in the F1 score, reaching 0.76 compared to prior research. The experiments further suggest that information retrieval-based approaches exhibit promising potential for this specific task.

CURRICULUM VITAE ANALYSIS USING MACHINE LEARNING ALGORITHM

We describe a system called CV analysis machine, that processes a set of given free-form textual resumes (in English for IT domain), creates a standardized profile for each candidate, and for a given job description, identifies a ranked shortlist of k candidates, along with a matching score for each. The resume scoring function is hand-crafted, hierarchical, and uses domain-knowledge from recruitment experts. We describe a simple neural- network system that automatically learns some weights used in the scoring function, based on feedback about whether the candidate has their grades on each portion and calculate the overall grade of each candidate and find all grades at a time. Companies often receive thousands of resumes for each job posting and employ dedicated screeners to short list qualified applicants. In this paper, we present PROSPECT, a decision support tool to help these screeners shortlist resumes efficiently. Prospect mines resumes to extract salient aspects of candidate profiles like skills, experience in each skill, education details and experience. Extracted information is presented in the form of facets to aid recruiters in the task of screening. We also employ Information Retrieval techniques to rank all applicants for a given job opening. In our experiments we show that extracted information improves our ranking by 30% there by making screening tasks simpler and more efficient. Keywords--e-recruitment,aptitude,personality prediction,credentials,Big five model of Personality

Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges

Recent years have witnessed a substantial increase in the use of deep learning to solve various natural language processing (NLP) problems. Early deep learning models were constrained by their sequential or unidirectional nature, such that they struggled to capture the contextual relationships across text inputs. The introduction of bidirectional encoder representations from transformers (BERT) leads to a robust encoder for the transformer model that can understand the broader context and deliver state-of-the-art performance across various NLP tasks. This has inspired researchers and practitioners to apply BERT to practical problems, such as information retrieval (IR). A survey that focuses on a comprehensive analysis of prevalent approaches that apply pretrained transformer encoders like BERT to IR can thus be useful for academia and the industry. In light of this, we revisit a variety of BERT-based methods in this survey, cover a wide range of techniques of IR, and group them into six high-level categories: (i) handling long documents, (ii) integrating semantic information, (iii) balancing effectiveness and efficiency, (iv) predicting the weights of terms, (v) query expansion, and (vi) document expansion. We also provide links to resources, including datasets and toolkits, for BERT-based IR systems. Additionally, we highlight the advantages of employing encoder-based BERT models in contrast to recent large language models like ChatGPT, which are decoder-based and demand extensive computational resources. Finally, we summarize the comprehensive outcomes of the survey and suggest directions for future research in the area.

Evaluation of Natural Language Processing Techniques for Information Retrieval

Purpose: The main objective of the study was to investigate the evaluation of Natural Language Processing techniques for information retrieval.
 Methodology: The study adopted a desktop research methodology. Desk research refers to secondary data or that which can be collected without fieldwork. Desk research is basically involved in collecting data from existing resources hence it is often considered a low cost technique as compared to field research, as the main cost is involved in executive’s time, telephone charges and directories. Thus, the study relied on already published studies, reports and statistics. This secondary data was easily accessed through the online journals and library.
 Findings: The findings reveal that there exists a contextual and methodological gap relating to Natural Language Processing techniques for information retrieval. Preliminary empirical review revealed that NLP methods significantly improved the accuracy and efficiency of information retrieval systems. Through systematic evaluation, various NLP techniques, including tokenization, named entity recognition, semantic parsing, and word embeddings, were found to enhance retrieval performance across diverse datasets and domains. By considering context and user intent, researchers aimed to develop more contextually aware and personalized information retrieval systems. The study emphasized the need for further research to explore hybrid approaches and domain-specific adaptations, ultimately highlighting the transformative potential of NLP in revolutionizing information access and utilization.
 Unique Contribution to Theory, Practice and Policy: Information Foraging theory, Relevance theory and Cognitive Load theory may be used to anchor future studies on Natural Language Processing techniques. The study provided recommendations to enhance information retrieval systems. It suggested integrating advanced NLP techniques such as named entity recognition and sentiment analysis to improve query understanding and document relevance. Additionally, the study recommended adopting word embeddings and semantic parsing techniques for better semantic understanding of user queries and documents. It emphasized the importance of domain-specific adaptations and continuous evaluation of NLP techniques to tailor them to specific application domains and keep pace with evolving user needs and technological advancements.

Unsupervised Extractive Summarization with Learnable Length Control Strategies

Unsupervised extractive summarization is an important technique in information extraction and retrieval. Compared with supervised method, it does not require high-quality human-labelled summaries for training and thus can be easily applied for documents with different types, domains or languages. Most of existing unsupervised methods including TextRank and PACSUM rely on graph-based ranking on sentence centrality. However, this scorer can not be directly applied in end-to-end training, and the positional-related prior assumption is often needed for achieving good summaries. In addition, less attention is paid to length-controllable extractor, where users can decide to summarize texts under particular length constraint. This paper introduces an unsupervised extractive summarization model based on a siamese network, for which we develop a trainable bidirectional prediction objective between the selected summary and the original document. Different from the centrality-based ranking methods, our extractive scorer can be trained in an end-to-end manner, with no other requirement of positional assumption. In addition, we introduce a differentiable length control module by approximating 0-1 knapsack solver for end-to-end length-controllable extracting. Experiments show that our unsupervised method largely outperforms the centrality-based baseline using a same sentence encoder. In terms of length control ability, via our trainable knapsack module, the performance consistently outperforms the strong baseline without utilizing end-to-end training. Human evaluation further evidences that our method performs the best among baselines in terms of relevance and consistency.

GPDminer: a tool for extracting named entities and analyzing relations in biological literature

PurposeThe expansion of research across various disciplines has led to a substantial increase in published papers and journals, highlighting the necessity for reliable text mining platforms for database construction and knowledge acquisition. This abstract introduces GPDMiner(Gene, Protein, and Disease Miner), a platform designed for the biomedical domain, addressing the challenges posed by the growing volume of academic papers.MethodsGPDMiner is a text mining platform that utilizes advanced information retrieval techniques. It operates by searching PubMed for specific queries, extracting and analyzing information relevant to the biomedical field. This system is designed to discern and illustrate relationships between biomedical entities obtained from automated information extraction.ResultsThe implementation of GPDMiner demonstrates its efficacy in navigating the extensive corpus of biomedical literature. It efficiently retrieves, extracts, and analyzes information, highlighting significant connections between genes, proteins, and diseases. The platform also allows users to save their analytical outcomes in various formats, including Excel and images.ConclusionGPDMiner offers a notable additional functionality among the array of text mining tools available for the biomedical field. This tool presents an effective solution for researchers to navigate and extract relevant information from the vast unstructured texts found in biomedical literature, thereby providing distinctive capabilities that set it apart from existing methodologies. Its application is expected to greatly benefit researchers in this domain, enhancing their capacity for knowledge discovery and data management.

RANCANG BANGUN APLIKASI STEGANOGRAFI UNTUK MENGAMANKAN PESAN MENGGUNAKAN METODE LEAST SIGNIFICANT BIT (LSB) BERBASIS ANDROID

The Internet, an interconnected network, has become one of the most widespread data communications medias in the world. With the development of various illegal information retrieval techniques, many people try to get information that does not belong to them. Various techniques to protect sensitive information from unauthorized persons are widely used to protect important information. Steganography is a technique for hiding message files from the public who know their existence. This technique is often used to avoid suspicion or people who want to know the contents of the message file. Steganography is the science and technique of writing hidden messages so that no one else knows about their existence. Therefore, the application of plain-text steganography is inserted into the Least Significant Bit (LSB) encrypted image carrier. This allows mobile users to send the author's message to the recipient securely..

Cultural Adaptation of Recipes

Abstract Building upon the considerable advances in Large Language Models (LLMs), we are now equipped to address more sophisticated tasks demanding a nuanced understanding of cross-cultural contexts. A key example is recipe adaptation, which goes beyond simple translation to include a grasp of ingredients, culinary techniques, and dietary preferences specific to a given culture. We introduce a new task involving the translation and cultural adaptation of recipes between Chinese- and English-speaking cuisines. To support this investigation, we present CulturalRecipes, a unique dataset composed of automatically paired recipes written in Mandarin Chinese and English. This dataset is further enriched with a human-written and curated test set. In this intricate task of cross-cultural recipe adaptation, we evaluate the performance of various methods, including GPT-4 and other LLMs, traditional machine translation, and information retrieval techniques. Our comprehensive analysis includes both automatic and human evaluation metrics. While GPT-4 exhibits impressive abilities in adapting Chinese recipes into English, it still lags behind human expertise when translating English recipes into Chinese. This underscores the multifaceted nature of cultural adaptations. We anticipate that these insights will significantly contribute to future research on culturally aware language models and their practical application in culturally diverse contexts.

Information Retrieval and Machine Learning Methods for Academic Expert Finding

In the context of academic expert finding, this paper investigates and compares the performance of information retrieval (IR) and machine learning (ML) methods, including deep learning, to approach the problem of identifying academic figures who are experts in different domains when a potential user requests their expertise. IR-based methods construct multifaceted textual profiles for each expert by clustering information from their scientific publications. Several methods fully tailored for this problem are presented in this paper. In contrast, ML-based methods treat expert finding as a classification task, training automatic text classifiers using publications authored by experts. By comparing these approaches, we contribute to a deeper understanding of academic-expert-finding techniques and their applicability in knowledge discovery. These methods are tested with two large datasets from the biomedical field: PMSC-UGR and CORD-19. The results show how IR techniques were, in general, more robust with both datasets and more suitable than the ML-based ones, with some exceptions showing good performance.

Classification and visualization: Twitter sentiment analysis of Malaysia’s private hospitals

Malaysia has many private’s hospitals. Thus, feedback is important to improve service quality, becoming reviews for other patients. Reviews use the channel service provided on social media, such as Twitter. Nevertheless, online reviews are unstructured and enormous in volume, which leads to difficulties in comparing private hospitals. In addition, no single websites compare private hospitals based on users’ interests, bilingual reviews, and less time-consuming. Due to that, this study aims to classify and visualize the Twitter sentiment analysis of private hospitals in Malaysia. The scope focuses on five factors: 1) administrative procedure, 2) cost, 3) communication, 4) expertise, and 5) service. Term frequency-inverse document frequency is used for text mining, information retrieval techniques, and the Naïve Bayes, a machine learning algorithm for the classification. The user can visualize the specified state’s private hospitals and compare them with any selected state. The system’s functionality and usability have been tested to ensure it meets the objectives. Functionality testing proved that the private hospital’s Twitter sentiment could be predicted based on the training and testing data as intended, with 77.13% and 77.96% accuracy for English and Bahasa Melayu, respectively, while the system usability scale based on the usability testing resulted in an average final score of 95.42%.

Content-based image retrieval based on corel dataset using deep learning

A popular technique for retrieving images from huge and unlabeled image databases are content-based-image-retrieval (CBIR). However, the traditional information retrieval techniques do not satisfy users in terms of time consumption and accuracy. Additionally, the number of images accessible to users are growing due to web development and transmission networks. As the result, huge digital image creation occurs in many places. Therefore, quick access to these huge image databases and retrieving images like a query image from these huge image collections provides significant challenges and the need for an effective technique. Feature extraction and similarity measurement are important for the performance of a CBIR technique. This work proposes a simple but efficient deep-learning framework based on convolutional-neural networks (CNN) for the feature extraction phase in CBIR. The proposed CNN aims to reduce the semantic gap between low-level and high-level features. The similarity measurements are used to compute the distance between the query and database image features. When retrieving the first 10 pictures, an experiment on the Corel-1K dataset showed that the average precision was 0.88 with Euclidean distance, which was a big step up from the state-of-the-art approaches.