Semantic Context Research Articles

Audiovisual perception of interrupted speech by nonnative listeners.

The purpose of the present study was to examine the influence of visual cues in audiovisual perception of interrupted speech by nonnative English listeners and to identify the role of working memory, long-term memory retrieval, and vocabulary knowledge in audiovisual perception by nonnative listeners. The participants included 31 Mandarin-speaking English learners between 19 and 41 years of age. The perceptual stimuli were noise-filled periodically interrupted AzBio and QuickSIN sentences with or without visual cues that showed a male speaker uttering the sentences. In addition to sentence recognition, the listeners completed a semantic fluency task, verbal (operation span) and visuospatial (symmetry span) working memory tasks, and two vocabulary knowledge tests (Vocabulary Level Test and Lexical Test for Advanced Learners of English). The results revealed significantly better speech recognition in the audio-visual condition than the audio-only condition, but the magnitude of visual benefit was substantially attenuated for sentences that had limited semantic context. The listeners' vocabulary size in English played a key role in the restoration of missing speech information and audiovisual integration in the perception of interrupted speech. Meanwhile, the listeners' verbal working memory capacity played an important role in audiovisual integration especially for the difficult stimuli with limited semantic context.

Face detection in contextual scenes.

Object and scene perception are intertwined. When objects are expected to appear within a particular scene, they are detected and categorised with greater speed and accuracy. This study examined whether such context effects also moderate the perception of social objects such as faces. Female and male faces were embedded in scenes with a stereotypical female or male context. Semantic congruency of these scene contexts influenced the categorisation of faces (Experiment 1). These effects were bi-directional, such that face sex also affected scene categorisation (Experiment 2), suggesting concurrent automatic processing of both levels. In contrast, the more elementary task of face detection was not affected by semantic scene congruency (Experiment 3), even when scenes were previewed prior to face presentation (Experiment 4). This pattern of results indicates that semantic scene context can affect categorisation of faces. However, the earlier perceptual stage of detection appears to be encapsulated from the cognitive processes that give rise to this contextual interference.

Exploiting Contextual Target Attributes for Target Sentiment Classification

In the past few years, pre-trained language models (PTLMs) have brought significant improvements to target sentiment classification (TSC). Existing PTLM-based models can be categorized into two groups: 1) fine-tuning-based models that adopt PTLM as the context encoder; 2) prompting-based models that transfer the classification task to the text/word generation task. Despite the improvements achieved by these models, we argue that they have their respective limitations. For fine-tuning-based models, they cannot make the best use of the PTLMs’ strong language modeling ability because the pre-train task and downstream fine-tuning task are not consistent. For prompting-based models, although they can sufficiently leverage the language modeling ability, it is hard to explicitly model the target-context interactions, which are widely realized as a crucial point of this task. In this paper, we present a new perspective of leveraging PTLM for TSC: simultaneously leveraging the merits of both language modeling and explicit target-context interactions via contextual target attributes. Specifically, we design the domain- and target-constrained cloze test, which can leverage the PTLMs’ strong language modeling ability to generate the given target’s attributes pertaining to the review context. The attributes contain the background and property information of the target, which can help to enrich the semantics of the review context and the target. To exploit the attributes for tackling TSC, we first construct a heterogeneous information graph by treating the attributes as nodes and combining them with (1) the syntax graph automatically produced by the off-the-shelf dependency parser and (2) the semantics graph of the review context, which is derived from the self-attention mechanism. Then we propose a heterogeneous information gated graph convolutional network to model the interactions among the attribute information, the syntactic information, and the contextual information. The experimental results on three benchmark datasets demonstrate the superiority of our model, which achieves new state-of-the-art performance.

A methodological approach for data standardization and management of Open Data portals for scientific research groups: a case study on mobile and ubiquitous ecosystems

IntroductionIn the scientific research domain, the Open Science movement stands as a fundamental pillar for advancing knowledge and innovation globally. This article presents the design and implementation of the GITCE Open Data Ecosystem (GITCE-ODE) Research Data Management System (RDMS), developed by the Research Group on Emerging Computational Technologies (GITCE) at the Technological University of Panama, as a platform for the long-term storage, publication, and dissemination of research products.MethodsThe architecture of the GITCE-ODE RDMS encompasses the entire data engineering lifecycle, facilitating information processing stages such as extraction, transformation, loading (ETL), as well as the management and analysis of diverse datasets and metadata.ResultsCompliance with the FAIR principles ensures that published data and products are Findable, Accessible, Interoperable, and Reusable, promoting automation in the discovery and reuse of digital resources. Key considerations of the web portal include file format standardization, data categorization, treatment of semantic context, and organization of resources to ensure efficient management and administration of open research data.DiscussionThrough this platform, GITCE aims to foster collaboration, transparency, and accessibility in scientific research, contributing to the ongoing advancement of knowledge transfer and innovation.

SOFB is a comprehensive ensemble deep learning approach for elucidating and characterizing protein-nucleic-acid-binding residues

Proteins and nucleic-acids are essential components of living organisms that interact in critical cellular processes. Accurate prediction of nucleic acid-binding residues in proteins can contribute to a better understanding of protein function. However, the discrepancy between protein sequence information and obtained structural and functional data renders most current computational models ineffective. Therefore, it is vital to design computational models based on protein sequence information to identify nucleic acid binding sites in proteins. Here, we implement an ensemble deep learning model-based nucleic-acid-binding residues on proteins identification method, called SOFB, which characterizes protein sequences by learning the semantics of biological dynamics contexts, and then develop an ensemble deep learning-based sequence network to learn feature representation and classification by explicitly modeling dynamic semantic information. Among them, the language learning model, which is constructed from natural language to biological language, captures the underlying relationships of protein sequences, and the ensemble deep learning-based sequence network consisting of different convolutional layers together with Bi-LSTM refines various features for optimal performance. Meanwhile, to address the imbalanced issue, we adopt ensemble learning to train multiple models and then incorporate them. Our experimental results on several DNA/RNA nucleic-acid-binding residue datasets demonstrate that our proposed model outperforms other state-of-the-art methods. In addition, we conduct an interpretability analysis of the identified nucleic acid binding residue sequences based on the attention weights of the language learning model, revealing novel insights into the dynamic semantic information that supports the identified nucleic acid binding residues. SOFB is available at https://github.com/Encryptional/SOFB and https://figshare.com/articles/online_resource/SOFB_figshare_rar/25499452.

The Impact of Intertextuality in Movies on Language Learning

This paper examines the effectiveness of using intertextuality in second language learning through movies. Two types of materials were prepared: first, the American animated movie <i>Shrek 2</i> (Adamson et al., 2004) was the primary material, and second, idioms from YouTube shorts were used as points of comparison for regular expressions found in <i>Shrek 2</i>. This case study involved five college students majoring in non-English subjects. Among them, one was at an intermediate level in English and four were at a low-intermediate level. After three months of participation, students underwent five tests: three language tests and two open-ended-question tests. The first three assessed recognition, salience, and memory. The results of the recognition and salience tests indicated that participants achieved perfect scores in regular expressions, thanks to intertextuality. The results of the memory test showed that idioms were remembered significantly better than regular expressions. However, this test suggested that intertextuality played a larger role in semantic contexts than in syntactic ones. In the first open-ended-question test, the participants successfully described both an original character and a new character in <i>Shrek 2</i>. The final question revealed that most participants appreciated two aspects of intertextuality: creative work and long-term memory gains.

Tone Tracker

Abstract: Tone Tracker's integration of BERT and LSTM technologies allows it to predict and flag offensive language in both Tamil and English social media comments. BERT, a transformer-based model, enables the tool to understand the semantic context of text in multiple languages, ensuring accurate detection of inappropriate content regardless of language. The incorporation of LSTM further enhances this capability by capturing nuanced contextual information, refining the tool's proficiency in content moderation for both Tamil and English content. With its user-friendly features, Tone Tracker becomes accessible to a diverse user base, empowering them to swiftly remove offensive content in both languages and contribute to fostering a secure digital environment. This groundbreaking innovation not only boosts content moderation efficiency but also ensures scalability across various digital platforms, making it adaptable to the linguistic diversity of online communities. Ultimately, Tone Tracker, powered by LSTM and BERT, plays a pivotal role in cultivating positive online spaces where users can engage confidently and respectfully in both Tamil and English.

Exploring large language model for generic and robust state-of-charge estimation of Li-ion batteries: A mixed prompt learning method

State-of-charge (SOC) estimation is important to ensure safe functioning of Li-ion batteries (LIBs). However, distinct measurements, harsh temperatures, and dynamic operations pose challenges in estimating intricate SOC changes of multiple LIBs with one estimator. Hence, this paper proposes a novel mixed prompt learning method to explore a large-scale pretrained language model (PLM) for SOC estimation. A new hard prompt generator is proposed to translate LIB data into instruction and answer text, eliciting the inherent representational capability of PLM to jointly learn the sequential patterns and contextual semantics of measurements through language modeling for accurate SOC estimation. A new soft prompt adapter is proposed to encode task-specific information of different LIBs into a small set of independent vectors, ensuring PLM adaptation with minimal parameters while maintaining good generalization. By integrating soft prompt vectors along the forward propagation, the hidden states of PLM are dynamically regulated to characterize volatile and variable SOC for robust estimation. Extensive experiments show that by leveraging mixed hard-soft prompts, PLM can make accurate, generic, and robust estimates for multiple LIBs simultaneously in subzero temperature, charge-pause-discharge, and low-capacity discharge scenarios, with the average MAE, RMSE, and MAX of all tasks as low as 1.20 %, 1.51 %, and 5.29 %, respectively.

Individual differences in the use of top-down versus bottom-up cues to resolve phonetic ambiguity.

How listeners weight a wide variety of information to interpret ambiguities in the speech signal is a question of interest in speech perception, particularly when understanding how listeners process speech in the context of phrases or sentences. Dominant views of cue use for language comprehension posit that listeners integrate multiple sources of information to interpret ambiguities in the speech signal. Here, we study how semantic context, sentence rate, and vowel length all influence identification of word-final stops. We find that while at the group level all sources of information appear to influence how listeners interpret ambiguities in speech, at the level of the individual listener, we observe systematic differences in cue reliance, such that some individual listeners favor certain cues (e.g., speech rate and vowel length) to the exclusion of others (e.g., semantic context). While listeners exhibit a range of cue preferences, across participants we find a negative relationship between individuals' weighting of semantic and acoustic-phonetic (sentence rate, vowel length) cues. Additionally, we find that these weightings are stable within individuals over a period of 1 month. Taken as a whole, these findings suggest that theories of cue integration and speech processing may fail to capture the rich individual differences that exist between listeners, which could arise due to mechanistic differences between individuals in speech perception.

Mapping method for complex mechatronic equipment relationship data to contextual semantic-constrained knowledge graphs

Complex mechatronic equipment’s complete life cycle information model includes multidimensional data on structure, qualities, behavior, and limitations. The data are diverse, derived from multiple sources, and include both streaming and non-streaming cyber-physical data. The product data system’s structured relational model, which is represented by the XBOM (X Bill of Material), is primarily where this data is stored. However, with the growing amount of equipment information, this relatively isolated and redundant architecture poses challenges. Within relational models, the growing intricacy of inner-outer key joins impedes effective data mining and retrieval for dynamic digital twin business applications. In response, this study proposes a knowledge graph transformation method that takes into account the semantic restrictions of the business application context to translate relational data to entities and semantic expressions. The method builds a knowledge context constraint meta-model by classifying data according to context semantics into one-hop entities, multi-hop entities, and abstract classes. Additionally, an ontology-based data extraction transformation method and an ontology-based mapping algorithm based on relational schema transformation are introduced in this article. This strategy significantly minimizes knowledge redundancy and enhances retrieval performance, as demonstrated by experimental verification through the development of a relational data mapping tool software.

Foreground bias: Semantic consistency effects modulated when searching across depth.

When processing visual scenes, we tend to prioritize information in the foreground, often at the expense of background information. The foreground bias has been supported by data demonstrating that there are more fixations to foreground, and faster and more accurate detection of targets embedded in foreground. However, it is also known that semantic consistency is associated with more efficient search. Here, we examined whether semantic context interacts with foreground prioritization, either amplifying or mitigating the effect of target semantic consistency. For each scene, targets were placed in the foreground or background and were either semantically consistent or inconsistent with the context of immediately surrounding depth region. Results indicated faster response times (RTs) for foreground and semantically consistent targets, replicating established effects. More importantly, we found the magnitude of the semantic consistency effect was significantly smaller in the foreground than background region. To examine the robustness of this effect, in Experiment 2, we strengthened the reliability of semantics by increasing the proportion of targets consistent with the scene region to 80%. We found the overall results pattern to replicate the incongruous effect of semantic consistency across depth observed in Experiment 1. This suggests foreground bias modulates the effects of semantics so that performance is less impacted in near space.

The priming effect of emotional words on body expressions: Two ERP studies

The impact of emotional words on the recognition of body expression and the underlying neurodynamic mechanisms remain poorly understood. This study used a classic supraliminal priming paradigm and event related potential (ERP) to investigate the effect of emotion-label words (experiment 1) and emotional verbs (experiment 2) on the recognition of body expressions. The behavioral results revealed that individuals exhibited a higher accuracy in recognizing happy expressions when presented with a happy-label word condition, in contrast to neutral expressions. Furthermore, it was observed that the accuracy of recognizing happy body expressions was reduced when preceded by angry verb priming, compared to happy and neutral priming conditions. Conversely, the accuracy of recognizing angry body expressions was higher in response to angry verb priming than happy and neutral primings. The ERP results showed that, in the recognition of happy body expressions, the P300 amplitude elicited by angry-label words was more positive, while a congruent verb-expression condition elicited more positive P300 amplitude than an incongruent condition in the left hemisphere and midline. However, in the recognition of angry body expressions, the N400 amplitude elicited by a congruent verb-expression condition was smaller than that elicited by an incongruent condition. These results suggest that both abstract emotion-label words and specific emotional verbs influence the recognition of body expressions. In addition, integrating happy semantic context and body expression might occur at the P300 stage, whereas integrating angry semantic context and body expression might occur at the N400 stage. These findings present novel evidence regarding the criticality of emotional context in the recognition of emotions.

Top-Heavy CapsNets Based on Spatiotemporal Non-Local for Action Recognition

To effectively comprehend human actions, we have developed a Deep Neural Network (DNN) that utilizes inner spatiotemporal non-locality to capture meaningful semantic context for efficient action identification. This work introduces the Top-Heavy CapsNet as a novel approach for video analysis, incorporating a 3D Convolutional Neural Network (3DCNN) to apply the thematic actions of local classifiers for effective classification based on motion from the spatiotemporal context in videos. This DNN comprises multiple layers, including 3D Convolutional Neural Network (3DCNN), Spatial Depth-Based Non-Local (SBN) layer, and Deep Capsule (DCapsNet). Firstly, the 3DCNN extracts structured and semantic information from RGB and optical flow streams. Secondly, the SBN layer processes feature blocks with spatial depth to emphasize visually advantageous cues, potentially aiding in action differentiation. Finally, DCapsNet is more effective in exploiting vectorized prominent features to represent objects and various action features for the ultimate label determination. Experimental results demonstrate that the proposed DNN achieves an average accuracy of 97.6%, surpassing conventional DNNs on the traffic police dataset. Furthermore, the proposed DNN attains average accuracies of 98.3% and 80.7% on the UCF101 and HMDB51 datasets, respectively. This underscores the applicability of the proposed DNN for effectively recognizing diverse actions performed by subjects in videos.

Evolving malware detection through instant dynamic graph inverse reinforcement learning

The rapid development and increasing evolution of malware necessitate novel defensive techniques with high accuracy and minimal false positives to safeguard information systems against potential threats. Unfortunately, current malware detection methods, primarily relying on deep learning to identify malicious fingerprints from extensive training sets, prove ineffective against few-shot and evolving malware variants. To address these challenges, this paper introduces MalIRL, which designs a model-free inverse reinforcement learning (IRL) mechanism to automatically capture the evolving attack intent of malware. Specifically, MalIRL explores six representative categories of malware actions and employs sliding windows to organically divide the massive malware execution event stream into multiple attack stages, achieving a reduced action space and state space. To model dynamic malicious environments, MalIRL proposes an instant dynamic heterogeneous graph representation learning technique. This technique learns state representations of different malware attack stages, enhancing detection accuracy and efficiency by incrementally capturing the newly added contextual semantics of diverse malware entities and relations. In experiments with three real-world malware datasets, MalIRL surpasses existing state-of-the-art methods, particularly in few-shot malware detection scenarios, MalIRL exhibits performance benefits of up to 18.9%.

Теоретико-методологический анализ правовой природы публичного контроля

Introduction. In modern legal science, there is no universal and uniform approach to defining the concept of “public control”, which predetermines and actualizes the need for a detailed study of the legal nature of this phenomenon, its content and the functions that it performs in the state and society. Theoretical analysis. The analysis of doctrinal approaches to disclosing the content of public control, formed in the system of legal science, allows us to draw a conclusion about a differentiated definition of this phenomenon. On the one hand, public control is considered as a combination of state and municipal types of control, which corresponds to the constitutional and legislative approaches to understanding public power. Another point of view complements the previous perspective with another type of control – public control, which involves the participation of civil society institutions in the implementation of this function of public authority. Empirical analysis. It has been revealed that the concept of “public control” is practically not used in the Russian legislation. At the same time, in judicial practice this category is often used in the texts of decisions of higher courts, but its interpretation, like that in the legal doctrine, is also very heterogeneous. Results. The assessment of the theory and practice of using the concept of “public control” allowed us to come to the following conclusions. The category of “public control”, in contrast to the term of “public power”, does not have a legal meaning, that is, it is not enshrined in the Russian legislation, which leads to the need to identify its theoretical significance only through the analysis of doctrinal approaches established in legal science. Based on the analysis of theoretical approaches to the meaning of public control, as well as materials from judicial practice, it is possible to conclude that this concept is used in a diametrically opposite semantic context. Applying the concept of public power as a combination of state, municipal and public ones, it is proposed to consider public control in a similar context, as a combination of state, municipal and public types of control.

Can Large Language Models Be Good Companions?

Developing chatbots as personal companions has long been a goal of artificial intelligence researchers. Recent advances in Large Language Models (LLMs) have delivered a practical solution for endowing chatbots with anthropomorphic language capabilities. However, it takes more than LLMs to enable chatbots that can act as companions. Humans use their understanding of individual personalities to drive conversations. Chatbots also require this capability to enable human-like companionship. They should act based on personalized, real-time, and time-evolving knowledge of their users. We define such essential knowledge as the common ground between chatbots and their users, and we propose to build a common-ground-aware dialogue system from an LLM-based module, named OS-1, to enable chatbot companionship. Hosted by eyewear, OS-1 can sense the visual and audio signals the user receives and extract real-time contextual semantics. Those semantics are categorized and recorded to formulate historical contexts from which the user's profile is distilled and evolves over time, i.e., OS-1 gradually learns about its user. OS-1 combines knowledge from real-time semantics, historical contexts, and user-specific profiles to produce a common-ground-aware prompt input into the LLM module. The LLM's output is converted to audio, spoken to the wearer when appropriate. We conduct laboratory and in-field studies to assess OS-1's ability to build common ground between the chatbot and its user. The technical feasibility and capabilities of the system are also evaluated. Our results show that by utilizing personal context, OS-1 progressively develops a better understanding of its users. This enhances user satisfaction and potentially leads to various personal service scenarios, such as emotional support and assistance.

JPSSL: SAR Terrain Classification Based on Jigsaw Puzzles and FC-CRF

Effective features play an important role in synthetic aperture radar (SAR) image interpretation. However, since SAR images contain a variety of terrain types, it is not easy to extract effective features of different terrains from SAR images. Deep learning methods require a large amount of labeled data, but the difficulty of SAR image annotation limits the performance of deep learning models. SAR images have inevitable geometric distortion and coherence speckle noise, which makes it difficult to extract effective features from SAR images. If effective semantic context features cannot be learned for SAR images, the extracted features struggle to distinguish different terrain categories. Some existing terrain classification methods are very limited and can only be applied to some specified SAR images. To solve these problems, a jigsaw puzzle self-supervised learning (JPSSL) framework is proposed. The framework comprises a jigsaw puzzle pretext task and a terrain classification downstream task. In the pretext task, the information in the SAR image is learned by completing the SAR image jigsaw puzzle to extract effective features. The terrain classification downstream task is trained using only a small number of labeled data. Finally, fully connected conditional random field processing is performed to eliminate noise points and obtain a high-quality terrain classification result. Experimental results on three large-scene high-resolution SAR images confirm the effectiveness and generalization of our method. Compared with the supervised methods, the features learned in JPSSL are highly discriminative, and the JPSSL achieves good classification accuracy when using only a small amount of labeled data.

Default mode network shows distinct emotional and contextual responses yet common effects of retrieval demands across tasks.

The default mode network (DMN) lies towards the heteromodal end of the principal gradient of intrinsic connectivity, maximally separated from the sensory-motor cortex. It supports memory-based cognition, including the capacity to retrieve conceptual and evaluative information from sensory inputs, and to generate meaningful states internally; however, the functional organisation of DMN that can support these distinct modes of retrieval remains unclear. We used fMRI to examine whether activation within subsystems of DMN differed as a function of retrieval demands, or the type of association to be retrieved, or both. In a picture association task, participants retrieved semantic associations that were either contextual or emotional in nature. Participants were asked to avoid generating episodic associations. In the generate phase, these associations were retrieved from a novel picture, while in the switch phase, participants retrieved a new association for the same image. Semantic context and emotion trials were associated with dissociable DMN subnetworks, indicating that a key dimension of DMN organisation relates to the type of association being accessed. The frontotemporal and medial temporal DMN showed a preference for emotional and semantic contextual associations, respectively. Relative to the generate phase, the switch phase recruited clusters closer to the heteromodal apex of the principal gradient-a cortical hierarchy separating unimodal and heteromodal regions. There were no differences in this effect between association types. Instead, memory switching was associated with a distinct subnetwork associated with controlled internal cognition. These findings delineate distinct patterns of DMN recruitment for different kinds of associations yet common responses across tasks that reflect retrieval demands.

Contextually Propagated Term Weight based Approach for Author Profiling: Gender, Age and Language Variety Prediction

Author profiling creates characterization of an author based on attributes such as age, gender, language, dialect region variety, personality and so on. In recent years it has garnered significant attention for its varies applications across forensic linguistics, marketing, cybersecurity and social media analytics. Most of the research focused on stylistic, content based and term weight measures based feature representations. We observed that context semantics is not considered in the feature representation. In this propose contextually propagated term weight measures for feature representation. We implemented SVM, Random Forest and XG Boost machine learning algorithms on those feature representations. The results demonstrated that the proposed contextually propagated term weight with inverse category frequency outperformed the existing methods.

An ontology of 3D environment where a simulated manipulation task takes place (ENVON)

Thanks to the advent of robotics in shopfloor and warehouse environments, control rooms need to seamlessly exchange information regarding the dynamically changing 3D environment to facilitate tasks and path planning for the robots. Adding to the complexity, this type of environment is heterogeneous as it includes both free space and various types of rigid bodies (equipment, materials, humans etc.). At the same time, 3D environment-related information is also required by the virtual applications (e.g., VR techniques) for the behavioral study of CAD-based product models or simulation of CNC operations. In past research, information models for such heterogeneous 3D environments are often built without ensuring connection among different levels of abstractions required for different applications. For addressing such multiple points of view and modelling requirements for 3D objects and environments, this paper proposes an ontology model that integrates the contextual, topologic, and geometric information of both the rigid bodies and the free space. The ontology provides an evolvable knowledge model that can support simulated task-related information in general. This ontology aims to greatly improve interoperability as a path planning system (e.g., robot) and will be able to deal with different applications by simply updating the contextual semantics related to some targeted application while keeping the geometric and topological models intact by leveraging the semantic link among the models.