Semantic Information Retrieval Research Articles

AttentiveBugLocator: A Bug Localization Model using Attention-based Semantic Features and Information Retrieval

AttentiveBugLocator: A Bug Localization Model using Attention-based Semantic Features and Information Retrieval

Evaluating Semantic and Personalized Information Retrieval with Deep Learning Models: A Performance Metrics Analysis

Evaluation of the Information Retrieval (IR) model is an important, complex process that involves evaluating many aspects of performance using quantitative measurements called evaluation metrics. This work explores the efficacy of Deep learning (DL) models in personalized and semantic information retrieval (SIR), an area that has witnessed significant advancements in the last few years. A thorough analysis of several DL models for search engine index retrieval is provided. The particular task, relevant standards, and desirable qualities, among others, influence the use of evaluation metrics in IR. A comprehensive evaluation of the performance of an IR system uses several metrics. The paper emphasizes how DL models can produce IR results that are more accurate, with an emphasis on choosing important metrics for evaluation. Among these metrics, on a given input query, a recall of 1.0 indicates full coverage in detecting pertinent cases, while a precision of 0.5 indicates 50% accuracy in positive predictions on a given input query. At 0.6667, the F1-score strikes a compromise between recall and precision. The model's ability to rank and prioritize is assessed by Mean Average Precision (MAP) at 0.5426 and Normalized Discounted Cumulative Gain (NDCG) at 0.8896. Precision in the top 5 suggestions is evaluated by Precision@5, which has a value of 0.6. This is important in situations where user attention or recommendation space are restricted. These measurements offer priceless information on the efficacy of IR models.

Development and Study of a Knowledge Graph for Retrieving the Relationship Between BVDV and Related Genes

Background: Bovine viral diarrhea virus (BVDV) can cause diarrhea, abortion, and immunosuppression in cattle, imposing huge economic losses for the global cattle industry. The pathogenic and immune mechanisms of BVDV remain elusive. The development of a BVDV-gene knowledge base can provide clues to reveal the interaction of BVDV with host cells. However, the traditional method of manually establishing a knowledge base is time-consuming and inefficient. The method of developing a knowledge base based on deep learning has noticeably attracted scholars' attention recently. Objective: The study aimed to explore the substitution of deep learning for manual mining of BVDVrelated genes and to develop a knowledge graph of the relationship between BVDV and related genes. Methods: A deep learning-based biomedical knowledge graph development method was proposed, which used deep learning to mine biomedical knowledge, model BVDV and various gene concepts, and store data in a graphical database. First, the PubMed database was used as the data source and crawler technology to obtain abstract data on the relationship between BVDV and various host genes. Pretrained BioBERT model was used for biomedical named entity recognition to obtain all types of gene entities, and the pre-trained BERT model was utilized for relationship extraction to achieve the relationship between BVDV and various gene entities. Then, it was combined with manual proofreading to obtain structured triple data with high accuracy. Finally, the Neo4j graph database was used to store data and to develop the knowledge graph of the relationship between BVDV and related genes. Results: The results showed the obtainment of 71 gene entity types, including PRL4, MMP-7, TGIF1, etc. 9 relation types of BVDV and gene entities were obtained, including "can downregulate expression of", "can upregulate expression of", "can suppress expression of", etc. The knowledge graph was developed using deep learning to mine biomedical knowledge combined with manual proofreading, which was faster and more efficient than the traditional method of establishing knowledge base manually, and the retrieval of semantic information by storing data in graph database was also more efficient. Conclusion: A BVDV-gene knowledge graph was preliminarily developed, which provided a basis for studying the interaction between BVDV and host cells.

Improving Semantic Information Retrieval Using Multinomial Naive Bayes Classifier and Bayesian Networks

This research proposes a new approach to improve information retrieval systems based on a multinomial naive Bayes classifier (MNBC), Bayesian networks (BNs), and a multi-terminology which includes MeSH thesaurus (Medical Subject Headings) and SNOMED CT (Systematized Nomenclature of Medicine of Clinical Terms). Our approach, which is entitled improving semantic information retrieval (IMSIR), extracts and disambiguates concepts and retrieves documents. Relevant concepts of ambiguous terms were selected using probability measures and biomedical terminologies. Concepts are also extracted using an MNBC. The UMLS (Unified Medical Language System) thesaurus was then used to filter and rank concepts. Finally, we exploited a Bayesian network to match documents and queries using a conceptual representation. Our main contribution in this paper is to combine a supervised method (MNBC) and an unsupervised method (BN) to extract concepts from documents and queries. We also propose filtering the extracted concepts in order to keep relevant ones. Experiments of IMSIR using the two corpora, the OHSUMED corpus and the Clinical Trial (CT) corpus, were interesting because their results outperformed those of the baseline: the P@50 improvement rate was +36.5% over the baseline when the CT corpus was used.

Quantifying the Dissimilarity of Texts

Quantifying the dissimilarity of two texts is an important aspect of a number of natural language processing tasks, including semantic information retrieval, topic classification, and document clustering. In this paper, we compared the properties and performance of different dissimilarity measures D using three different representations of texts—vocabularies, word frequency distributions, and vector embeddings—and three simple tasks—clustering texts by author, subject, and time period. Using the Project Gutenberg database, we found that the generalised Jensen–Shannon divergence applied to word frequencies performed strongly across all tasks, that D’s based on vector embedding representations led to stronger performance for smaller texts, and that the optimal choice of approach was ultimately task-dependent. We also investigated, both analytically and numerically, the behaviour of the different D’s when the two texts varied in length by a factor h. We demonstrated that the (natural) estimator of the Jaccard distance between vocabularies was inconsistent and computed explicitly the h-dependency of the bias of the estimator of the generalised Jensen–Shannon divergence applied to word frequencies. We also found numerically that the Jensen–Shannon divergence and embedding-based approaches were robust to changes in h, while the Jaccard distance was not.

Aging-related effects on the controlled retrieval of semantic information.

The efficient use of knowledge requires semantic control processes to retrieve context-relevant information. So far, it is well-established that semantic knowledge, as measured with vocabulary tests, does not decline with aging. Yet, it is still unclear whether controlled retrieval-the context-driven retrieval of very specific aspects of semantic knowledge-deteriorates in aging, following the same fate as other forms of cognitive control. Here, we tackled this issue by comparing the performance of younger and older native Italian speakers during a semantic feature verification task. To manipulate the control demands, we parametrically varied the semantic salience of the target feature for the cue concept. As compared to their young counterparts, older adults showed worse performance (in terms of reaction times) as the salience of the target feature of the concept decreased. This result suggests that older people have relatively greater difficulties in regulating the activation within semantic representation when conditions pose high demands of controlled retrieval of semantic information. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Font disfluency and reading performance in children: An event-related potential study

Expert adult readers process fluent and disfluent fonts differently, at both early perceptual and late higher-order processing stages. This finding has been interpreted as reflecting the more difficult to read disfluent fonts requiring greater neural resources. We aimed to investigate whether neural activity is affected by font disfluency in pre-adolescent readers, and to determine if neural responses are related to reading performance. Thirty-three participants between 8 and 12 years old completed two one-back tasks using letter and word stimuli, where font was manipulated (fluent versus disfluent stimuli), during which electroencephalography was recorded. Event related potentials (ERPs) were calculated relative to non-target stimuli for both tasks. The Woodcock Johnson III Tests of Achievement reading specific tests, and the Castles and Coltheart Test 2 were also collected. Font (fluent versus disfluent stimuli) did not consistently affect neural activity during both the letter and word tasks. Fluent stimuli elicited greater late activity (450–600 ms) than disfluent stimuli during the word task, suggesting easy-to-read fonts may enhance the maintenance of words in visual working memory and facilitate the retrieval of semantic information. However, reading performance was not associated with neural disfluency effects, suggesting that pre-adolescents are still at an early developmental reading period. Font manipulation may be a useful way to track developmental reading trajectories in the brain.

Improving semantic information retrieval by combining possibilistic networks, vector space model and pseudo-relevance feedback

To improve the performance of information retrieval systems (IRSs), we propose in this article a novel approach that enriches the user’s queries with new concepts. Indeed, query expansion is one of the best methods that plays an important role in improving searches for a better semantic information retrieval. The proposed approach in this study combines possibilistic networks (PNs), the vector space model (VSM) and pseudo-relevance feedback (PRF) to evaluate and add relevant concepts to the initial index of the user’s query. First, query expansion is performed using PN, VSM and domain knowledge. PRF is then exploited to enrich, in a second round, the user’s query by applying the same approach used in the first expansion step. To evaluate the performance of the developed system, denoted conceptual information retrieval model (CIRM), several experiments of query expansion are performed. The experiments carried out on the OHSUMED and Clinical Trials corpora showed that using the two measures of possibility and necessity combined the cosinus similarity and PRF improves the query expansion process. Indeed, the improvement rate of our approach compared with the baseline is +28, 49% in terms of P@5.

On bridging consumer health search across languages using cross-lingual word space

Information search is a lucrative activity for electronic commerce, contributing to significant revenues. As search engine becomes the primary source for seeking health information, the search quality concerns consumers. Specifically, the health vocabulary used by general consumers differs from the professionals, leading to unsatisfied retrieval performance and misleading information. The situation is increasingly complex when consumers search health information across languages. To study consumer health search (CHS) across languages, we propose a cross-lingual retrieval framework comprising semantic space construction and information retrieval modules. The semantic space construction module adopts a weakly-supervised approach to determine a cross-lingual word space (CLWS) from collected consumer-generated health content, which helps capture consumers’ vocabulary and identify medical expression translations. The information retrieval module suggests strategies that utilize the translations of CLWS for the subsequent retrieval tasks. By evaluating the performance on two health information search engines, we found that Google Translate (GT), a widely-adopted translation service, is prone to generate mistranslations to the colloquial medical expressions. The CLWS helps identify GT’s mistranslations and filter out the results retrieved by those. More importantly, our framework demonstrates a strategy to integrate translations of CLWS and GT to reach the best retrieval performance for the cross-lingual CHS task.

Verbal Fluency in Prelingually Deaf, Early Implanted Children and Adolescents With Cochlear Implants.

Verbal fluency tasks assess the ability to quickly and efficiently retrieve words from the mental lexicon by requiring subjects to rapidly generate words within a phonological or semantic category. This study investigated differences between cochlear implant users and normal-hearing peers in the clustering and time course of word retrieval during phonological and semantic verbal fluency tasks. Twenty-eight children and adolescents (aged 9-17 years) with cochlear implants and 33 normal-hearing peers completed measures of verbal fluency, nonverbal intelligence, speech perception, and verbal short-term/working memory. Phonological and semantic verbal fluency tests were scored for total words generated, words generated in each 10-s interval of the 1-min task, latency to first word generated, number of word clusters, average cluster size, and number of word/cluster switches. Children and adolescents with cochlear implants generated fewer words than normal-hearing peers throughout the entire 60-s time interval of the phonological and semantic fluency tasks. Cochlear implant users also had slower start latency times and produced fewer clusters and switches than normal-hearing peers during the phonological fluency task. Speech perception and verbal working memory scores were more strongly associated with verbal fluency scores in children and adolescents with cochlear implants than in normal-hearing peers. Cochlear implant users show poorer phonological and semantic verbal fluency than normal-hearing peers, and their verbal fluency is significantly associated with speech perception and verbal working memory. These findings suggest deficits in fluent retrieval of phonological and semantic information from long-term lexical memory in cochlear implant users.

AR Search Engine: Semantic Information Retrieval for Augmented Reality Domain

With the emergence of the metaverse, the popularity of augmented reality (AR) is increasing; accessing concise, accurate, and precise information in this field is becoming challenging on the world wide web. In regard to accessing the right information through search engines, semantic information retrieval via a semantic analysis delivers more relevant information pertaining to the user’s query. However, there is insufficient research on developing semantic information retrieval methods in the AR domain that ranks and clusters AR-based search results in a fair fashion. This paper develops an AR search engine that automatically organizes, understands, searches, and summarizes web documents to enhance the relevancy scores in AR domains. The engine enables users to organize and manage relevant AR documents in various AR concepts and efficiently discover more accurate results in terms of relevancy in the AR field. First, we propose an AR ontology for clustering AR documents into AR topics and concepts. Second, we developed an ontology-based clustering method using the k-means clustering algorithm, vector space model, and term frequency-inverse document frequency (TF-IDF) weighting model with ontology to explore and cluster the AR documents. Third, an experiment was designed to evaluate the proposed AR search engine and compare it with the custom search engine in the AR domains. The results showed that the AR search engine accessed the right information about 42.33% faster and with a 34% better ranking.

Ontology-based semantic retrieval of documents using Word2vec model

Semantic retrieval of engineering knowledge is crucial in various engineering activities, such as process development and product model planning. To make a solution for this issue, previously, a few word-based semantic enabling existing approaches such as Lexical Retrieval Model with Semantic Residual Embedding’s (LR-SRE), Document Retrieval Model through Semantic Linking (DR-MTS), Semantic Term Matching in Axiomatic Approaches to Information Retrieval (STM-IR) and Hybrid Ontology for Semantic Information Retrieval Model using Keyword Matching Indexing System (HOS-IR) were utilized. But, they all have shown less query-based accuracy results than the required value. In our proposed Information Retrieval (IR) design, the semantic knowledge-based retrieval scheme has been implemented. For query, entered by a user and processed for finding the dominated word. Word is then compared for its similarity equations, and similarity values are then computed to give output. Highly similar values are obtained as the class value. From class, the respective clusters are selected. Then, documents in that cluster are retrieved and ranked according to the relevance of the user. To support the accuracy level performance of this IR system, a word2vec model has been employed with the benefits of Horse Herd Optimization (HHO), which helps to extract vectors as features for classification. These results are stored as a .csv file for further retrieval. By implementing the proposed IR-word2vec model, the results showed that it outperforms other existing techniques by improved similarity index and accuracy for query results in an execution time of 1.7 s.

Intact memory storage but impaired retrieval in visual memory in autism: New insights from an electrophysiological study.

In a recent study on visual episodic memory (Desaunay, Clochon, et al., 2020), we have shown event-related potentials (ERPs) differences associated with priming (150-300 msec), familiarity (350-470 msec), and recollection (600-700 msec), in young people with autism spectrum disorders (ASD) compared with typical development (TD). To go further into the study of the processes of storage and retrieval of the memory trace, we re-analyzed Desaunay, Clochon, et al's data using time-frequency analysis, that is, event-related synchronization and desynchronization (ERS/ERD). This allows a decomposition of the spectral power within frequency bands associated with these ERPs. We focused both on the same time windows and the same regions of interest as previously published. We mainly identified, in ASD compared with TD, reduced ERS in low-frequencies (delta, theta) in early time-windows, and non-significant differences in ERD in higher frequencies (alpha, beta1) in all time-windows. Reduced ERS during recognition confirmed previously reported diminution of priming effects and difficulties in manipulation and retrieval of both semantic and episodic information. Conversely, preserved ERD corroborates a preservation of memory storage processes. These observations are consistent with a cognitive model of memory in ASD, that suggests difficulties in cognitive operations or executive demand at retrieval, subsequent to successful long-term storage of information. LAY SUMMARY: We assessed the EEG synchronization and desynchronization, during visual episodic recognition. We observed, in youth with Autism, reduced synchronization in low-frequencies (delta, theta), suggesting reduced access to and manipulation of long-term stored information. By contrast, non-significant differences in desynchronization at higher frequencies (alpha, beta frequency bands), that support long-term stored semantic and episodic information, suggested preserved memory traces.

Specificity in Generalization Effects of Transcranial Direct Current Stimulation Over the Left Inferior Frontal Gyrus in Primary Progressive Aphasia

ObjectivesGeneralization (or near-transfer) effects of an intervention to tasks not explicitly trained are the most desirable intervention outcomes. However, they are rarely reported and even more rarely explained. One hypothesis for generalization effects is that the tasks improved share the same brain function/computation with the intervention task. We tested this hypothesis in this study of transcranial direct current stimulation (tDCS) over the left inferior frontal gyrus (IFG) that is claimed to be involved in selective semantic retrieval of information from the temporal lobes. Materials and MethodsIn this study, we examined whether tDCS over the left IFG in a group of patients with primary progressive aphasia (PPA), paired with a lexical/semantic retrieval intervention (oral and written naming), may specifically improve semantic fluency, a nontrained near-transfer task that relies on selective semantic retrieval, in patients with PPA. ResultsSemantic fluency improved significantly more in the active tDCS than in the sham tDCS condition immediately after and two weeks after treatment. This improvement was marginally significant two months after treatment. We also found that the active tDCS effect was specific to tasks that require this IFG computation (selective semantic retrieval) but not to other tasks that may require different computations of the frontal lobes. ConclusionsWe provided interventional evidence that the left IFG is critical for selective semantic retrieval, and tDCS over the left IFG may have a near-transfer effect on tasks that depend on the same computation, even if they are not specifically trained. Clinical Trial RegistrationThe Clinicaltrials.gov registration number for the study is NCT02606422.

Creativity in verbal associations is linked to semantic control.

Although memory is known to play a key role in creativity, previous studies have not isolated the critical component processes and networks. We asked participants to generate links between words that ranged from strongly related to completely unrelated in long-term memory, delineating the neurocognitive processes that underpin more unusual versus stereotypical patterns of retrieval. More creative responses to strongly associated word-pairs were associated with greater engagement of episodic memory: in highly familiar situations, semantic, and episodic stores converge on the same information enabling participants to form a personal link between items. This pattern of retrieval was associated with greater engagement of core default mode network (DMN). In contrast, more creative responses to weakly associated word-pairs were associated with the controlled retrieval of less dominant semantic information and greater recruitment of the semantic control network, which overlaps with the dorsomedial subsystem of DMN. Although both controlled semantic and episodic patterns of retrieval are associated with activation within DMN, these processes show little overlap in activation. These findings demonstrate that controlled aspects of semantic cognition play an important role in verbal creativity.

Hybrid optimized query expansion strategy for semantic information retrieval using spatial bound whale and binary moth flame optimization algorithm

SummaryThe standard information retrieval systems mainly extract documents based on the relative keywords and this method is not effective since the related information can be only identified by extracting the semantics present in the text. Hence to overcome this problem, a semantic‐based query retrieval model is formulated in this article for query processing, identification, extraction, expansion, sorting, and filtering. A keyword expansion approach using the hybrid spatial bound whale optimization algorithm‐binary moth flame optimization algorithm is proposed in this work. In this way, the complexity associated with insufficient query information is overcome. The efficiency of the proposed model in extracting the top k relevant information is evaluated using the experiments conducted in the TREC data using different performance metrics such as precision@k, recall@k, mean reciprocal rank@k, mean average precision, and normalized discounted cumulative gain (NDCG@k). The proposed model achieves improved outcomes when compared to different state‐of‐art techniques such as i‐Dataquest, fuzzy logic, ontological framework for information extraction, and personal knowledge management in terms of precision@k, recall@k, mean reciprocal rank@k, exact match, F1‐score, and NDCG@k. The proposed model gives a mean reciprocal rank@k score of 0.8901, 0.8947, 0.8958, and 0.9014 for the k‐values 1, 3, 5, and 10, respectively. The MAP@k score for the top‐10 result suggestion retrieved is 0.39056. The exact match score of the proposed model for the newsgroup, SQuAD 1.0, and SQUAD 2.0 is 93.25, 94.65, and 95.25.

Effect of familiarity and recollection during constrained retrieval on incidental encoding for new "foil" information.

Behavioral studies have demonstrated differences in the effect of constrained retrieval of semantic vs. non-semantic information on the encoding of foils. However, the impact of recognition on foils between semantic and non-semantic trials remains unclear. This study thus examines the roles of recognition—familiarity and recollection—in constrained retrieval for foils. We applied the event-related brain potentials (ERPs) data of new/old effects to elucidate the neural mechanisms underlying the “foil effect.” Participants encoded semantic and non-semantic tasks (Phase 1), were tested in a blocked memory task with new words presented as foils (Phase 2), and performed a surprise recognition task involving foils and completely new words (Phase 3). Behavioral results showed better recognition performance regarding reaction times and accuracy by hit and correct reject for semantic vs. non-semantic trials in Phase 2. Conversely, inferior recognition performance in reaction times and accuracy by hit and correct reject was noted for semantic vs. non-semantic foils in Phase 3. ERP results showed more positive Frontal N400 (FN400) for hit in non-semantic trials, more positive late positive component (LPC) for correct rejects in semantic trials in Phase 2, and more positive LPC for hits in both semantic and non-semantic trials only in Phase 3. Through dual-processing theory, we prove that different task types in constrained retrieval depend on different retrieval processes. Particularly, familiarity may be applied more often in non-semantic trials, and recollection in semantic trials. The difference in processes between semantic and non-semantic trials during constrained retrieval affects incidental encoding of foils.

Two dichotomies of recognition memory.

Murdock (1974, Human Memory: Theory and Data, Lawrence Erlbaum) distinguished between the encoding and retrieval of item information (the representation of individual events) and associative information (the representation of relations between separate events). Mandler (1980, Psychological Review, 87, 252-271) proposed that recognition decisions could be based on the sense of familiarity engendered by the stimulus or on the retrieval of conceptual, semantic, and contextual information about the target. These two distinctions have motivated a considerable amount of research over the past 40 years and have provided much of the bases for our current understanding of recognition memory. Selective aspects of this research are reviewed to show how theories of recognition memory have developed to embody these two dichotomies. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Vision-based method for semantic information extraction in construction by integrating deep learning object detection and image captioning

Recently, vision-based monitoring has been widely adopted in construction management to improve crew productivity, reduce safety risks, and facilitate site planning. However, automated retrieval of semantic information (e.g., objects, activities, and interactions between objects) from construction images remains challenging due to the complex nature of construction sites. This paper proposes a novel semantic information extraction method by integrating deep learning object detection and image captioning, which aims to explore salient information from construction images or videos. In the proposed method, object detection has been employed as an encoder to extract the feature maps of construction object zones and the holistic image. The image captioning has been selected as the decoder to extract the semantic information. A post-processing method has been proposed to parse the semantic information into a graph format for better accessibility and visualization. In experiments, the proposed method has achieved the Consensus-based Image Description Evaluation (CIDEr) of 1.84. By adopting the proposed method, semantic information behind construction images can be presented to construction managers to assist their decision-making.

What determines cognitive estimation ability? Changing contributions of semantic and executive domains as a function of age.

The Cognitive Estimation Test (CET) is commonly used in neuropsychological assessment. It is typically assumed to load on executive functions, although research has shown that CET performance also depends on access to semantic knowledge. It is unknown whether these contributions vary with age. It is important to examine this question as these abilities have divergent life course trajectories: executive functions tend to decline as people age but semantic knowledge continues to accrue. In addition, previous research has not examined potential contributions to CET performance from semantic control abilities, that is cognitive control processes involved specifically in the retrieval and use of semantic information. To address these questions, we investigated cognitive predictors of CET performance in healthy young and older adults. We found that better executive function was associated with more accurate estimation in both age groups. However, the effect of semantic knowledge on CET performance was significantly larger in older people, having no predictive power in the younger group. The ability to detect weak semantic associations, which is thought to index controlled search and retrieval of semantic information, also had divergent effects on CET performance in the two age groups. Our results provide empirical support for the idea that older people are more reliant on semantic knowledge when estimating quantities, which may explain why age‐related decline in CET scores is not typically found. We conclude that deficits on the CET may be indicative either of semantic or executive impairments, particularly in older age groups.