Interpretation Tasks Research Articles

Active learning with deep autoencoders for seismic facies interpretation

Machine-learning (ML)-assisted seismic interpretation tasks require large quantities of labeled data annotated by expert interpreters, which is a costly and time-consuming process. Whereas existing works to minimize dependence on labeled data assume the data annotation process to already be completed, active learning — a field of ML — works by selecting the most important training samples for the interpreter to annotate in real time simultaneously with the training of the interpretation model itself, resulting in high levels of performance with fewer labeled data samples than otherwise possible. Whereas there exists significant literature on active learning for classification tasks with respect to natural images, there exists very little to no work for dense prediction tasks in geophysics such as interpretation. We have developed a unique and first-of-its-kind active learning framework for seismic facies interpretation using the manifold learning properties of deep autoencoders. By jointly learning representations for supervised and unsupervised tasks and then ranking unlabeled samples by their nearness to the data manifold, we can identify the most relevant training samples to be labeled by the interpreter in each training round. On the popular F3 data set, we obtain close to a 10% point difference in terms of the interpretation accuracy between the proposed method and the baseline with only three fully annotated seismic sections.

Short report: Social processing in non-emotional contexts by children with and without autism spectrum disorders (ASD).

Children with autism spectrum disorders (ASD) have been reported to show social-processing deficits in forced-choice social judgment or story interpretation tasks. However, these methods may limit examination of social-processing within a set of acceptable answers. In this pilot study, we propose a novel method predicated on the premise that language carries social information and validate this method to measure social perception in ASD. 20 children with ASD and 20 typically developing (TD) children matched-pairwise on age (5-12 years), gender, and non-verbal IQ, described pictures of people in everyday situations varying on extent of social engagement. Their social language production was examined in high- and low-social picture conditions. The TD group produced significantly more social language in high-social than low-social picture conditions, with a large effect size (d = 3.15). The TD group produced significantly more social language than the ASD group under high-social conditions (p< .001, η2p = 0.24), but were not significantly different under low-social conditions (p < .05). The study presents proof-of-concept that expressed language carries social information. The findings indicate that social language may be used to measure social perception and examine differences in ASD, with potential applications for other clinical groups with social-processing challenges.

ClinoformNet-1.0: stratigraphic forward modeling and deep learning for seismic clinoform delineation

Abstract. Deep learning has been widely used for various kinds of data-mining tasks but not much for seismic stratigraphic interpretation due to the lack of labeled training datasets. We present a workflow to automatically generate numerous synthetic training datasets and take the seismic clinoform delineation as an example to demonstrate the effectiveness of using the synthetic datasets for training. In this workflow, we first perform stochastic stratigraphic forward modeling to generate numerous stratigraphic models of clinoform layers and corresponding porosity properties by randomly but properly choosing initial topographies, sea level curves, and thermal subsidence curves. We then convert the simulated stratigraphic models into impedance models by using the velocity–porosity relationship. We further simulate synthetic seismic data by convolving reflectivity models (converted from impedance models) with Ricker wavelets (with various peak frequencies) and adding real noise extracted from field seismic data. In this way, we automatically generate a total of 3000 diverse synthetic seismic datasets and the corresponding stratigraphic labels such as relative geologic time models and facies of clinoforms, which are all made publicly available. We use these synthetic datasets to train a modified encoder–decoder deep neural network for clinoform delineation in seismic data. Within the network, we apply a preconditioning process of structure-oriented smoothing to the feature maps of the decoder neural layers, which is helpful to avoid generating holes or outliers in the final output of clinoform delineation. Multiple 2D and 3D synthetic and field examples demonstrate that the network, trained with only synthetic datasets, works well to delineate clinoforms in seismic data with high accuracy and efficiency. Our workflow can be easily extended for other seismic stratigraphic interpretation tasks such as sequence boundary identification, synchronous horizon extraction, and shoreline trajectory identification.

Machine learning-based cement integrity evaluation with a through-tubing logging experimental setup

Assessing the integrity of the cement layer and the quality of its bond to the casing and formation is paramount to ensure that the wellbore is hydraulically isolated from the surrounding environment before permanently sealing the well. Such inspection is part of Plugging & Abandonment (P&A) operations, and it is usually achieved through well logging tools, which provide a vast amount of data that a skilled specialist interprets. The process is human-dependent, error-prone, and time-consuming. There has been an increasing interest in solutions that allow an automatic interpretation of the logging data since the recent panorama of the oil and gas industry indicates a growing P&A demand. Such solutions aim at reducing the dependence on human knowledge and consequently increasing the reliability and accuracy of the cement integrity evaluation. Therefore, this work presents an experimental setup capable of emulating defective cement layer configurations of real-world oil wells in single or multi-string arrangements. Such flexibility enables acquiring logging data for multiple well conditions and building a rich logging database to develop a supervised learning framework and define the most suitable model for performing the cement integrity evaluation. Several logging runs were performed, producing a database with 130 samples, including varied tubing eccentricity levels and cement layer conditions. A complete analysis of the data both in the time domain as well as in the frequency–wavenumber domain was performed, highlighting the complexity of the interpretation task. A resampling-based workflow was employed to evaluate machine learning models of different families. The models were tested under three scenarios, and accuracy and computational complexity metrics were computed to compare their performance. The results showed that shallow learning models can perform satisfactorily well even with less data available for training. The support vector machine stood out, achieving a mean accuracy score higher than 0.99 while being able to predict the cement sheath’s condition in less than 1 ms. This paper contributes to the research on the cement integrity evaluation by presenting a study that combines an experimental setup mimicking several oil well conditions and the employment of machine learning as a diagnostic tool, which has no precedents in recent literature regarding the acoustic logging knowledge field.

AST: Adaptive Self-supervised Transformer for optical remote sensing representation

Due to the variation in spatial resolution and the diversity of object scales, the interpretation of optical remote sensing images is extremely challenging. Deep learning has become the mainstream solution to interpret such complex scenes. However, the explosion of deep learning model architectures has resulted in the need for hundreds of millions of remote sensing images for which labels are very costly or often unavailable publicly. This paper provides an in-depth analysis of the main reasons for this data thirst, i.e., (i) limited representational power for model learning, and (ii) underutilization of unlabeled remote sensing data. To overcome the above difficulties, we present a scalable and adaptive self-supervised Transformer (AST) for optical remote sensing image interpretation. By performing masked image modeling in pre-training, the proposed AST releases the rich supervision signals in massive unlabeled remote sensing data and learns useful multi-scale semantics. Specifically, a cross-scale Transformer architecture is designed to collaboratively learn global dependencies and local details by introducing a pyramid structure, to facilitate multi-granular feature interactions and generate scale-invariant representations. Furthermore, a masking token strategy relying on correlation mapping is proposed to achieve adaptive masking of partial patches without affecting key structures, which enhances the understanding of visually important regions. Extensive experiments on various optical remote sensing interpretation tasks show that AST has good generalization capability and competitiveness.

Meta-Knowledge Guided Weakly Supervised Instance Segmentation for Optical and SAR Image Interpretation

The interpretation of optical and synthetic aperture radar (SAR) images in remote sensing is general for many tasks, such as environmental monitoring, marine management, and resource planning. Instance segmentation of optical and SAR images, which can simultaneously provide instance-level localization and pixel-level classification of objects of interest, is a crucial and challenging task in image interpretation. Considering that most current methods for instance segmentation of optical and SAR images rely on expensive pixel-level annotation, we develop a weakly supervised instance segmentation (WSIS) method to balance the visual processing requirements with the annotation cost. First, we decompose the prior knowledge of the mask-aware task in WSIS into three meta-knowledge components: fundamental knowledge, apparent knowledge, and detailed knowledge inspired by human visual perception habits of “whole to part” and “coarse to detailed.” Then, a meta-knowledge-guided weakly supervised instance segmentation network (MGWI-Net) is proposed. In this network, the weakly supervised mask (WSM) head can instantiate both fundamental knowledge and apparent knowledge to perform mask awareness without any annotations at the pixel level. The network also includes a mask information awareness assist (MIAA) head, which can implicitly guide the network to learn detailed information about edges through the boundary-sensitive feature of the fully connected conditional random field (CRF), facilitating the instantiation of detailed knowledge. The experimental results show that the MGWI-Net can efficiently generate instance masks for optical and SAR images and achieve the approximate instance segmentation results of the fully supervised method with about one-eighth of the annotation production time. The model parameters and processing speed of our network are also competitive. This study can provide inexpensive and convenient technical support for applying and promoting instance segmentation methods for optical and SAR images.

SpongEffects: ceRNA modules offer patient-specific insights into the miRNA regulatory landscape.

Cancer is one of the leading causes of death worldwide. Despite significant improvements in prevention and treatment, mortality remains high for many cancer types. Hence, innovative methods that use molecular data to stratify patients and identify biomarkers are needed. Promising biomarkers can also be inferred from competing endogenous RNA (ceRNA) networks that capture the gene-miRNA gene regulatory landscape. Thus far, the role of these biomarkers could only be studied globally but not in a sample-specific manner. To mitigate this, we introduce spongEffects, a novel method that infers subnetworks (or modules) from ceRNA networks and calculates patient- or sample-specific scores related to their regulatory activity. We show how spongEffects can be used for downstream interpretation and machine learning tasks such as tumor classification and for identifying subtype-specific regulatory interactions. In a concrete example of breast cancer subtype classification, we prioritize modules impacting the biology of the different subtypes. In summary, spongEffects prioritizes ceRNA modules as biomarkers and offers insights into the miRNA regulatory landscape. Notably, these module scores can be inferred from gene expression data alone and can thus be applied to cohorts where miRNA expression information is lacking. https://bioconductor.org/packages/devel/bioc/html/SPONGE.html. are available at Bioinformatics online.

The Qurʾān and the Future of Islamic Analytic Theology

Islamic analytic theology emerges into an uncharted territory that is dominated by two loosely defined areas: analytic philosophy and analytic theology. As a nascent field, this article argues that for Islamic analytic theology to move forward, it needs to place the Qurʾān at its centre. To have a clear understanding of our terms, I begin by attempting a definition of Islamic analytic theology. Taking a normative approach to the subject, I consolidate the discussion with five methodical questions. Firstly, what has been going on in Islamic theology? (The descriptive task). Secondly, why has this been going on? (The interpretative task). Thirdly, what ought to be going on? (The normative task). Fourthly, how might we, as Muslim theologians, respond? (The pragmatic task). Fifthly, why should Muslim theologians conduct analytic theology? (The functional task) To situate Islamic analytic theology within this wider discussion, I end the article by offering some insights on how Islamic analytic theology relates to old Kalām. By the end of the article, we will have laid the groundwork showing the way forward for a more developed Islamic analytic theology.

Development and task-based evaluation of a scatter-window projection and deep learning-based transmission-less attenuation compensation method for myocardial perfusion SPECT.

Attenuation compensation (AC) is beneficial for visual interpretation tasks in single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI). However, traditional AC methods require the availability of a transmission scan, most often a CT scan. This approach has the disadvantage of increased radiation dose, increased scanner costs, and the possibility of inaccurate diagnosis in cases of misregistration between the SPECT and CT images. Further, many SPECT systems do not include a CT component. To address these issues, we developed a Scatter-window projection and deep Learning-based AC (SLAC) method to perform AC without a separate transmission scan. To investigate the clinical efficacy of this method, we then objectively evaluated the performance of this method on the clinical task of detecting perfusion defects on MPI in a retrospective study with anonymized clinical SPECT/CT stress MPI images. The proposed method was compared with CT-based AC (CTAC) and no-AC (NAC) methods. Our results showed that the SLAC method yielded an almost overlapping receiver operating characteristic (ROC) plot and a similar area under the ROC (AUC) to the CTAC method on this task. These results demonstrate the capability of the SLAC method for transmission-less AC in SPECT and motivate further clinical evaluation.

Serial image interpretation tasks improve accuracy and increase confidence in Level 1 echocardiography reporting: a pilot study

BackgroundFocused echocardiography is increasingly used in acute and emergency care, with point-of-care ultrasound integrated into several specialist training curricula (e.g. Emergency Medicine, Cardiology, Critical Care). Multiple accreditation pathways support development of this skill but there is scant empirical evidence to inform selection of teaching methods, accreditation requirements or quality assurance of education in focussed echocardiography. It has also been noted that access to in-person teaching can be a barrier to completing accreditation programmes, and that this may affect learners disproportionately depending on the location or nature of their institution. The purpose of the study was to determine whether serial image interpretation tasks as a distinct learning tool improved novice echocardiographers’ ability to accurately identify potentially life-threatening pathology from focused scans. We also aimed to describe the relationship between accuracy of reporting and participants’ confidence in those reports, and to assess users’ satisfaction with a learning pathway that could potentially be delivered remotely.Methods27 participants from a variety of healthcare roles completed a program of remote lectures and 2 in-person study days. During the program they undertook 4 ‘packets’ of 10 focused echocardiography reporting tasks (total = 40) based on images from a standardised dataset. Participants were randomized to view the scans in varying orders. Reporting accuracy was compared with consensus reports from a panel of expert echocardiographers, and participants self-reported confidence in their image interpretation and their satisfaction with the learning experience.ResultsThere was a stepwise improvement in reporting accuracy with each set of images reported, from an average reporting score of 66% for the 1st packet to 78% for the 4th packet. Participants felt more confident in identifying common life-threatening pathologies as they reported more echocardiograms. The correlation between report accuracy and confidence in the report was weak and did not increase during the study (rs = 0.394 for the 1st packet, rs = 0.321 for the 4th packet). Attrition during the study related primarily to logistical issues. There were high levels of satisfaction amongst participants, with most reporting that they would use and / or recommend a similar teaching package to colleagues.ConclusionsHealthcare professionals undertaking remote training with recorded lectures, followed by multiple reporting tasks were capable of interpreting focused echocardiograms. Reporting accuracy and confidence in identifying life-threatening pathology increased with the number of scans interpreted. The correlation between accuracy and confidence for any given report was weak (and this relationship should be explored further given the potential safety considerations). All components of this package could be delivered via distance learning to enhance the flexibility of echocardiography education.

Competency Standard Derivation for Point-of-Care Ultrasound Image Interpretation for Emergency Physicians.

Because number-based standards are increasingly controversial, the objective of this study was to derive a performance-based competency standard for the image interpretation task of point-of-care ultrasound (POCUS). This was a prospective study. Operating on a clinically-relevant sample of POCUS images, we adapted the Ebel standard-setting method to derive a performance benchmark in 4 diverse pediatric POCUS applications: soft tissue, lung, cardiac and focused assessment with sonography in trauma (FAST). In Phase I (difficulty calibration), cases were categorized into interpretation difficulty terciles (easy, intermediate, hard) using emergency physician-derived data. In Phase II (significance), a 4-person expert panel categorized cases as low, medium, or high clinical significance. In Phase III (standard setting), a 3x3 matrix was created, categorizing cases by difficulty and significance, and a 6-member panel determined acceptable accuracy for each of the 9 cells. An overall competency standard was derived from the weighted sum. We obtained data from 379 emergency physicians resulting in 67,093 interpretations and a median of 184 (interquartile range, 154, 190) interpretations per case. There were 78 (19.5%) easy, 272 (68.0%) medium, and 50 (12.5%) hard-to-interpret cases, and 237 (59.3%) low, 65 (16.3%) medium, and 98 (24.5%) cases of high clinical significance across the 4 POCUS applications. The panel determined an overall performance-based competency score of 85.0% for lung, 89.5% for cardiac, 90.5% for soft tissue, and 92.7% for FAST. This research provides a transparent chain of evidence that derived clinically relevant competency standards for POCUS image interpretation.

입력처리 교수가 한국 중학교 영어 학습자의 관계대명사 학습에 미치는 영향

This study aims to explore the effects of Processing Instruction (PI) on learning English relative pronouns by middle school third graders compared to Traditional Instruction (TI). Pre-test, post-test, and delayed post-test measures involving an interpretation task and a sentence-level production task were analyzed to examine the effects of learners’ target grammar learning and their long-term retention. For statistical analyses of the data, paired samples t-test and repeated measures ANOVA were performed. The results demonstrated that PI had immediate positive effects on the subjects’ interpretation and production of relative pronouns, whereas TI did so on their production only. For the high-level proficiency groups, only PI learners showed a significant improvement in both interpretation and production of the target grammar. For the low-level proficiency groups, both PI and TI did not have positive effects on interpretation. The positive effects of instruction were maintained over time for both groups.

P2FEViT: Plug-and-Play CNN Feature Embedded Hybrid Vision Transformer for Remote Sensing Image Classification

Remote sensing image classification (RSIC) is a classical and fundamental task in the intelligent interpretation of remote sensing imagery, which can provide unique labeling information for each acquired remote sensing image. Thanks to the potent global context information extraction ability of the multi-head self-attention (MSA) mechanism, visual transformer (ViT)-based architectures have shown excellent capability in natural scene image classification. However, in order to achieve powerful RSIC performance, it is insufficient to capture global spatial information alone. Specifically, for fine-grained target recognition tasks with high inter-class similarity, discriminative and effective local feature representations are key to correct classification. In addition, due to the lack of inductive biases, the powerful global spatial context representation capability of ViT requires lengthy training procedures and large-scale pre-training data volume. To solve the above problems, a hybrid architecture of convolution neural network (CNN) and ViT is proposed to improve the RSIC ability, called P2FEViT, which integrates plug-and-play CNN features with ViT. In this paper, the feature representation capabilities of CNN and ViT applying for RSIC are first analyzed. Second, aiming to integrate the advantages of CNN and ViT, a novel approach embedding CNN features into the ViT architecture is proposed, which can make the model synchronously capture and fuse global context and local multimodal information to further improve the classification capability of ViT. Third, based on the hybrid structure, only a simple cross-entropy loss is employed for model training. The model can also have rapid and comfortable convergence with relatively less training data than the original ViT. Finally, extensive experiments are conducted on the public and challenging remote sensing scene classification dataset of NWPU-RESISC45 (NWPU-R45) and the self-built fine-grained target classification dataset called BIT-AFGR50. The experimental results demonstrate that the proposed P2FEViT can effectively improve the feature description capability and obtain outstanding image classification performance, while significantly reducing the high dependence of ViT on large-scale pre-training data volume and accelerating the convergence speed. The code and self-built dataset will be released at our webpages.

Applications of Artificial Intelligence in the Radiology Roundtrip: Process Streamlining, Workflow Optimization, and Beyond

There are many impactful applications of artificial intelligence (AI) in the electronic radiology roundtrip and the patient's journey through the healthcare system that go beyond diagnostic applications. These tools have the potential to improve quality and safety, optimize workflow, increase efficiency, and increase patient satisfaction. In this article, we review the role of AI for process improvement and workflow enhancement which includes applications beginning from the time of order entry, scan acquisition, applications supporting the image interpretation task, and applications supporting tasks after image interpretation such as result communication. These non-diagnostic workflow and process optimization tasks are an important part of the arsenal of potential AI tools that can streamline day to day clinical practice and patient care.

Revisiting artificial intelligence diagnosis of hepatocellular carcinoma with DIKWH framework.

Hepatocellular carcinoma (HCC) is the most common type of liver cancer with a high morbidity and fatality rate. Traditional diagnostic methods for HCC are primarily based on clinical presentation, imaging features, and histopathology. With the rapid development of artificial intelligence (AI), which is increasingly used in the diagnosis, treatment, and prognosis prediction of HCC, an automated approach to HCC status classification is promising. AI integrates labeled clinical data, trains on new data of the same type, and performs interpretation tasks. Several studies have shown that AI techniques can help clinicians and radiologists be more efficient and reduce the misdiagnosis rate. However, the coverage of AI technologies leads to difficulty in which the type of AI technology is preferred to choose for a given problem and situation. Solving this concern, it can significantly reduce the time required to determine the required healthcare approach and provide more precise and personalized solutions for different problems. In our review of research work, we summarize existing research works, compare and classify the main results of these according to the specified data, information, knowledge, wisdom (DIKW) framework.

"Hermenautics": Toward a Disinformation Theory

Abstract: This essay tracks cybernetic approaches to the task of hermeneutics. From the first paradigm of cybernetics through its development within contemporary lines of research, the question of information processing evokes problems of interpretation shared by humans and machines. The article discusses Friedrich Kittler's notion of "hermenautics" in the context of disinformation and contemporary politics. This argument draws out connections between scientist Heinz Von Foerster's writings on the ethics of second-order cybernetics and Hannah Arendt's reporting on the trial of Adolf Eichmann. Regimes of disinformation, working to blunt the task of interpretation, are only intensified by the information age. The study of cybernetics can prepare us for the task of adapting hermeneutics to an age of digital dissemination, reading (with) machines.

Fault characterization in a postsalt reservoir interval, Jubarte Field (Campos Basin), using seismic attributes and machine learning

Seismic attributes are routinely applied to interpretation tasks to improve the recognition of geologic features in the subsurface. Subtle changes in the amplitude and phase components of the seismic data can reveal details and provide information about the management of hydrocarbon reservoirs. To this end, we investigate how instantaneous and geometric attributes can help in fault and discontinuity recognition. Seismic data from Jubarte’s 4D/4C Permanent Reservoir Monitoring system, offshore Brazil, were used to test the impact of a variety of algorithms and parameters in improving fault visualization. The presence of seismic noise and geologic units with weak acoustic impedance contrasts motivated the application of additional methods such as data conditioning workflows and unsupervised machine learning methods. We found that spectral balancing and structure-oriented filtering increased the lateral continuity of some stratigraphic reflectors and attenuated the random noise, which improved fault surface visibility. Attributes were calculated on the full-stack data and azimuth-restricted volumes revealing different impacts of the seismic noise and changes in the lateral continuity of the features. In some cases, faults are better delineated when the acquisition direction is oriented perpendicular (or nearly) to the discontinuity. In addition, the most-positive and most-negative curvature components indicate more details of major features. A large number of seismic cubes and attributes motivated the use of principal component analysis and self-organizing maps, which complement the identification of fault segments with clusters composed of specific neurons aligned within structural discontinuities. The improvements obtained in terms of fault visualization demonstrate the importance of having a workflow that combines different fault and fracture identification methods. An integrated study is important as it identifies effects related to seismic noise and stratigraphic features. For the Jubarte Field, a multiattribute approach demonstrates advantages for delimiting the lateral extension of faults and a more precise discontinuity location.

LuoJiaAI: A cloud-based artificial intelligence platform for remote sensing image interpretation

ABSTRACT The rapid processing, analysis, and mining of remote-sensing big data based on intelligent interpretation technology using remote-sensing cloud computing platforms (RS-CCPs) have recently become a new trend. The existing RS-CCPs mainly focus on developing and optimizing high-performance data storage and intelligent computing for common visual representation, which ignores remote sensing data characteristics such as large image size, large-scale change, multiple data channels, and geographic knowledge embedding, thus impairing computational efficiency and accuracy. We construct a LuoJiaAI platform composed of a standard large-scale sample database (LuoJiaSET) and a dedicated deep learning framework (LuoJiaNET) to achieve state-of-the-art performance on five typical remote sensing interpretation tasks, including scene classification, object detection, land-use classification, change detection, and multi-view 3D reconstruction. The details of the LuoJiaAI application experiment can be found at the white paper for LuoJiaAI industrial application. In addition, LuoJiaAI is an open-source RS-CCP that supports the latest Open Geospatial Consortium (OGC) standards for better developing and sharing Earth Artificial Intelligence (AI) algorithms and products on benchmark datasets. LuoJiaAI narrows the gap between the sample database and deep learning frameworks through a user-friendly data-framework collaboration mechanism, showing great potential in high-precision remote sensing mapping applications.

Teaching students how to interpret animal emotions part 1: in the classroom and on placement

Identifying the patient's emotional state enables veterinary nurses to tailor care, provide better advice on animal training and behaviour problems, and stay safe during human–animal interactions. However, the ability to interpret animal emotions is not instinctive and must be learnt. This article refers to Herrington and Oliver's ‘authentic learning framework’, which may be used in the classroom and during clinical placements to structure teaching and learning. For example, classroom-based teaching could transmit appropriate knowledge (‘scaffolding’), demonstrate the interpretation process (provide ‘access to expert performance’ and ‘modelling’) and task students with identifying animal emotions in images and YouTube videos (‘authentic activities’). Within clinical placement, supervisors could activate their students' knowledge by using questioning, model their own process of identifying animal emotions (‘access to expert performance’), and set authentic learning activities such as an audit of animals' emotions. Within both contexts, reflection and discussion should be encouraged, coaching provided as necessary, and authentic assessment used to gauge student ability. Placement supervisors can build their formal knowledge of animal emotions by reviewing their students' learning materials, attending animal behaviour conferences or webinars, accessing reliable websites and reading academic journal articles. This would also count towards their annual continuing veterinary education requirements. Part 2 of this article will discuss putting into practice what has been learned.

Характеристика интерпретаций и преобразований в вариантах «Сказки о попе и о работнике его Балде» А. С. Пушкина

The research aims to characterise a set of transformations in the variants of “The Tale of the Priest and of His Workman Balda” by A. Pushkin in the content-related and aesthetic aspects, interpretations of this fairy tale and its variants by types of interpretation of the text. The paper contains a list of transformations in the variants of A. Pushkin’s fairy tale, describes the results of alterations of the fairy tale in the content-related and aesthetic aspects, identifies the types of interpretations of the fairy tale and its variants in accordance with the tasks of interpretation from the XX century to the present day. Scientific novelty lies in the fact that the comparison of the invariant of this fairy tale by A. Pushkin with its variants in linguistic Russian studies, as well as in philology in general has not been carried out, meanwhile the said fairy tale belongs to the number of cultural capital texts. As a result, it has been determined that the technique of re-naming objects prevails among the transformations. V. Zhukovsky carried out a qualitative transformation of the fairy tale for publication. In the Russian discourse of the XIX-XXI centuries, the recognising, reproductive, normative interpretations are presented in relation to Pushkin’s fairy tale as a cultural capital text and its variants.