Search Results (155)

This study presents the first systematic evaluation of in-context learning for Tarifit machine translation, a low-resource Amazigh language spoken by 5 million people in Morocco and Europe. We assess three large language models (GPT-4, Claude-3.5, PaLM-2) across Tarifit–Arabic, Tarifit–French, and Tarifit–English translation using 1000 sentence pairs and 5-fold cross-validation. Results show that 8-shot similarity-based demonstration selection achieves optimal performance. GPT-4 achieved 20.2 BLEU for Tarifit–Arabic, 14.8 for Tarifit–French, and 10.9 for Tarifit–English. Linguistic proximity significantly impacts translation quality, with Tarifit–Arabic substantially outperforming other language pairs by 8.4 BLEU points due to shared vocabulary and morphological patterns. Error analysis reveals systematic issues with morphological complexity (42% of errors) and cultural terminology preservation (18% of errors). This work establishes baseline benchmarks for Tarifit translation and demonstrates the viability of in-context learning for morphologically complex low-resource languages, contributing to linguistic equity in AI systems. Full article

The role of emotional intelligence (EI) in the academic context has been steadily established, together with its impact on students’ academic achievement, well-being, and professional success. Therefore, this study examined the development of a key EI ability—emotional understanding—throughout secondary school and explored its impact on students’ academic achievement (maternal language and mathematics) at the end of this cycle, using the Vocabulary of Emotions Test. A total of 222 students were followed over the entire 3-year secondary cycle, using a three-wave longitudinal design spanning from 10th to 12th grade. At the first wave, participants were aged between 14 and 18 years (M = 15.4; SD = 0.63), with 58.6% being female. Overall, the results of Latent Growth Curve modeling indicated that students’ emotional understanding increased over the secondary school cycle. While student’s gender predicted the emotional understanding change patterns throughout secondary school, student’s GPA in 10th grade did not. Moreover, the initial levels of ability-based emotional understanding predicted students’ achievement in maternal language at the end of the cycle. Our findings offer valuable insights into how EI skills can contribute to academic endeavors in late adolescence and will explore their impact on educational settings. Full article

Object detection in drone-captured imagery has attracted significant attention due to its wide range of real-world applications, including surveillance, disaster response, and environmental monitoring. Although the majority of existing methods are developed under closed-set assumptions, and some recent studies have begun to explore open-vocabulary or open-world detection, their application to UAV imagery remains limited and underexplored. In this paper, we address this limitation by exploring the relationship between images and textual semantics to extend object detection in UAV imagery to an open-vocabulary setting. We propose a novel and efficient detector named Unmanned Aerial Vehicle Open-Vocabulary Detector (UAV-OVD), specifically designed for drone-captured scenes. To facilitate open-vocabulary object detection, we propose improvements from three complementary perspectives. First, at the training level, we design a region–text contrastive loss to replace conventional classification loss, allowing the model to align visual regions with textual descriptions beyond fixed category sets. Structurally, building on this, we introduce a multi-level text-guided fusion decoder that integrates visual features across multiple spatial scales under language guidance, thereby improving overall detection performance and enhancing the representation and perception of small objects. Finally, from the data perspective, we enrich the original dataset with synonym-augmented category labels, enabling more flexible and semantically expressive supervision. Experiments conducted on two widely used benchmark datasets demonstrate that our approach achieves significant improvements in both mean mAP and Recall. For instance, for Zero-Shot Detection on xView, UAV-OVD achieves 9.9 mAP and 67.3 Recall, 1.1 and 25.6 higher than that of YOLO-World. In terms of speed, UAV-OVD achieves 53.8 FPS, nearly twice as fast as YOLO-World and five times faster than DetrReg, demonstrating its strong potential for real-time open-vocabulary detection in UAV imagery. Full article

Unmanned Aerial Vehicle (UAV) image semantic segmentation faces challenges in recognizing novel categories due to closed-set training paradigms and the high cost of annotation. While open-vocabulary semantic segmentation (OVSS) leverages vision-language models like CLIP to enable flexible class recognition, existing methods are limited to low-resolution images, hindering their applicability to high-resolution UAV data. Current adaptations—downsampling, cropping, or modifying CLIP—compromise either detail preservation, global context, or computational efficiency. To address these limitations, we propose HR-Seg, the first high-resolution OVSS framework for UAV imagery, which effectively integrates global context from downsampled images with local details from cropped sub-images through a novel cost-volume architecture. We introduce a detail-enhanced encoder with multi-scale embedding and a detail-aware decoder for progressive mask refinement, specifically designed to handle objects of varying sizes in aerial imagery. We evaluated existing OVSS methods alongside HR-Seg, training on the VDD dataset and testing across three benchmarks: VDD, UDD, and UAVid. HR-Seg achieved superior performance with mIoU scores of 89.38, 73.67, and 55.23, respectively, outperforming all compared state-of-the-art OVSS approaches. These results demonstrate HR-Seg’s exceptional capability in processing high-resolution UAV imagery. Full article

Large-language-model (LLM) APIs demonstrate impressive reasoning capabilities, but their size, cost, and closed weights limit the deployment of knowledge-aware AI within biomedical research groups. At the other extreme, standard attention-based neural language models (SANLMs)—including encoder–decoder architectures such as Transformers, Gated Recurrent Units (GRUs), and Long Short-Term Memory (LSTM) networks—are computationally inexpensive. However, their capacity for semantic reasoning in noisy, open-vocabulary knowledge bases (KBs) remains unquantified. Therefore, we investigate whether compact SANLMs can (i) reason over hybrid OpenIE-derived KBs that integrate commonsense, general-purpose, and non-communicable-disease (NCD) literature; (ii) operate effectively on commodity GPUs; and (iii) exhibit semantic coherence as assessed through manual linguistic inspection. To this end, we constructed four training KBs by integrating ConceptNet (600k triples), a 39k-triple general-purpose OpenIE set, and an 18.6k-triple OpenNCDKB extracted from 1200 PubMed abstracts. Encoder–decoder GRU, LSTM, and Transformer models (1–2 blocks) were trained to predict the object phrase given the subject + predicate. Beyond token-level cross-entropy, we introduced the Meaning-based Selectional-Preference Test (MSPT): for each withheld triple, we masked the object, generated a candidate, and measured its surplus cosine similarity over a random baseline using word embeddings, with significance assessed via a one-sided t-test. Hyperparameter sensitivity (311 GRU/168 LSTM runs) was analyzed, and qualitative frame–role diagnostics completed the evaluation. Our results showed that all SANLMs learned effectively from the point of view of the cross entropy loss. In addition, our MSPT provided meaningful semantic insights: for the GRUs (256-dim, 2048-unit, 1-layer): mean similarity $\left({\mu }_{sts}\right)$ of 0.641 to the ground truth vs. 0.542 to the random baseline (gap 12.1%; $p<{10}^{-180}$). For the 1-block Transformer: ${\mu }_{sts}=0.551$ vs. $0.511$ (gap 4%; $p<{10}^{-25}$). While Transformers minimized loss and accuracy variance, GRUs captured finer selectional preferences. Both architectures trained within <24 GB GPU VRAM and produced linguistically acceptable, albeit over-generalized, biomedical assertions. Due to their observed performance, LSTM results were designated as baseline models for comparison. Therefore, properly tuned SANLMs can achieve statistically robust semantic reasoning over noisy, domain-specific KBs without reliance on massive LLMs. Their interpretability, minimal hardware footprint, and open weights promote equitable AI research, opening new avenues for automated NCD knowledge synthesis, surveillance, and decision support. Full article

This paper describes the development and testing of a classroom and complementary home-based intervention to build preschoolers’ spatial orientation skills, focusing on exploring implementation feasibility and initial child learning outcomes. Spatial orientation, one type of spatial thinking, involves understanding the relationship between spatial positions, using maps and models to represent and navigate through space, and using spatial vocabulary. Evidence continues to accumulate that gaining spatial skills helps overall mathematics achievement and that learning resources are needed in this field. This mixed-methods study is the third in a series of investigations that leverage a design-based implementation research approach to develop preschool resources to support spatial orientation with both hands-on and technology-based experiences. Through a quasi-experimental comparison study, treatment teachers implemented eight weeks of hands-on activities, read-aloud stories, and digital activities (including an augmented reality app) and a sample of families also engaged in complementary home-based activities. The findings suggest that the resources help teachers feasibly implement spatial lessons, and preschoolers improve their learning of spatial concepts with the use of the classroom and home-based intervention. Full article

Generative tools often lack the guidance of scientific design methods in the design of non-heritage products. This study proposes a new Stingray model, which collects perceptual vocabularies of modeling and other aspects by integrating the perceptual engineering method to clarify the design direction and establishes the design objectives by ranking the importance of the vocabularies using the Analytic Hierarchy Process (AHP) hierarchical analysis method. Taking the Joon County clay sculpture as an example, this study uses generative tools to achieve the innovation of packaging patterns, selects sustainable materials such as straw to complete the sustainable non-heritage packaging design, and verifies its feasibility using the TOPSIS method. The results show that the new Stingray model effectively integrates multiple design methods and solves the subjectivity and feasibility deficiencies of a single model. Meanwhile, the system-guided generative tool significantly improved design efficiency and simplified program adjustment. This study provides theoretical support for generative tools and opens a new path for the sustainable development of non-heritage packaging. Full article

Sustainability is a modern design philosophy, and this concept prompted this study to focus on the possibility of achieving sustainability principles practically by using artificial intelligence techniques to create sustainable contemporary furniture elements inspired by the heritage and arts of Arabic calligraphy. Heritage-inspired design has cultural meaning and significance as a type of sustainable thinking. Arabic calligraphy has multiple forms and the possibility of adapting it, in addition to its role in enriching the cultural and creative stock. This study aimed to benefit from Arabic calligraphy as a source to enrich and sustain furniture design that is characterized by authenticity and modernity, and to preserve a heritage design product by reformulating it using artificial intelligence methods. In a way that enhances belonging and preserves the community’s heritage and values from extinction, this study followed the descriptive analytical approach in identifying the origins and characteristics of Arabic calligraphy, analyzing its vocabulary, reformulating it, and drawing inspiration from it to enrich furniture designs, in addition to the experimental approach in the applied study through the use of different techniques and materials. The results of this study concluded that there are various aesthetic values in the use of Arabic calligraphy that can be used to create contemporary furniture designs using artificial intelligence techniques to preserve its sustainability. In addition to opening up broad possibilities for creativity and innovation by integrating Arabic calligraphy into furniture design using artificial intelligence technology, this study recommended the need to pay attention to studying the sustainability of heritage and arts in general in appreciation of art and its preservation. Full article

This paper examines the ability of ChatGPT to generate synthetic comment datasets that mimic those produced by humans. To this end, a collection of datasets containing human comments, freely available in the Kaggle repository, was compared to comments generated via ChatGPT. The latter were based on prompts designed to provide the necessary context for approximating human results. It was hypothesized that the responses obtained from ChatGPT would demonstrate a high degree of similarity with the human-generated datasets with regard to vocabulary usage. Two categories of prompts were analyzed, depending on whether they specified the desired length of the generated comments. The evaluation of the results primarily focused on the vocabulary used in each comment dataset, employing several analytical measures. This analysis yielded noteworthy observations, which reflect the current capabilities of ChatGPT in this particular task domain. It was observed that ChatGPT typically employs a reduced number of words compared to human respondents and tends to provide repetitive answers. Furthermore, the responses of ChatGPT have been observed to vary considerably when the length is specified. It is noteworthy that ChatGPT employs a smaller vocabulary, which does not always align with human language. Furthermore, the proportion of non-stop words in ChatGPT’s output is higher than that found in human communication. Finally, the vocabulary of ChatGPT is more closely aligned with human language than the similarity between the two configurations of ChatGPT. This alignment is particularly evident in the use of stop words. While it does not fully achieve the intended purpose, the generated vocabulary serves as a reasonable approximation, enabling specific applications such as the creation of word clouds. Full article

The actiotope model of giftedness takes a systems approach to understand the development of exceptionality and, more broadly, the academic achievement of students. Focusing primarily on the interactions between environmental capitals and outcomes such as academic achievement, research has relied on methods such as structural equation modelling (SEM) to understand these interactions. However, such methods do not reflect the nonlinear interactions inherent within systems. Based on datasets obtained from students from one Australian school (n = 778), both SEM and artificial neural networks (ANNs) were created for school-assessed achievement scores (mathematics, english and science) and standardised test scores (mathematics, vocabulary, and reading). Using the optimal ANN for school-assessed achievement scores for mathematics, its potential to predict future scores based on hypothetical improvements to five of the 11 capitals was confirmed. With high quality data, the use of ANNs will allow researchers to better understand these interactions and support practitioners to implement evidence-based interventions. Full article

With the rapid expansion of the Electric Sport Utility Vehicle (ESUV) market, capturing consumer aesthetic preferences and emotional needs through front-end styling has become a key issue in automotive design. However, traditional Kansei Engineering (KE) approaches suffer from limited timeliness, subjectivity, and low predictive accuracy when extracting affective vocabulary and modeling the nonlinear relationship between product form and Kansei imagery. To address these challenges, this study proposes an improved KE-based ESUV styling framework that integrates data mining, machine learning, and generative AI. First, real consumer reviews and front-end styling samples are collected via Python-based web scraping. Next, the Biterm Topic Model (BTM) and Analytic Hierarchy Process (AHP) are used to extract representative Kansei vocabulary. Subsequently, the Back Propagation Neural Network (BPNN) and Support Vector Regression (SVR) models are constructed and optimized using the Seagull Optimization Algorithm (SOA) and Particle Swarm Optimization (PSO). Experimental results show that SOA-BPNN achieves superior predictive accuracy. Finally, Stable Diffusion is applied to generate ESUV design schemes, and the optimal model is employed to evaluate their Kansei imagery. The proposed framework offers a systematic and data-driven approach for predicting consumer affective responses in the conceptual styling stage, effectively addressing the limitations of conventional experience-based design. Thus, this study offers both methodological innovation and practical guidance for integrating affective modeling into ESUV styling design. Full article

Fisheries management is a complex task aiming to ensure the long-term sustainability of fish populations and the ecosystems they depend on. To achieve those goals, it is essential that the fisheries are described with precise and non-ambiguous information. Different agencies are reporting fisheries data by relying on several vocabularies or thesauri. Just indicatively, for the description of aquatic species, there are different official and widely used data sources that can be used. As a result, there are different identifiers or names for describing the same resource. In this paper, we describe the construction of a global aquatic resource knowledge base, which is the result of the integration of different data sources using semantic web technologies. By focusing on aquatic species, we show that the information provided by different data sources is complementary, and we provide a unified way for accessing them. We finally describe how the same process was adopted for other information domains as well. Full article

Word games are of great importance in the acquisition of vocabulary and letter recognition among children, usually between the ages of 3 and 13, boosting their memory, word retention, spelling, and cognition. Despite the importance of these games, little attention has been paid to the development of word games for low-resource or highly morphologically constructed languages. This study develops an Advanced Cubic-oriented Game (ACG) model by using a character-level N-gram technique and statistics, commonly known as the matching letter game, wherein a player forms words using a given number of cubes with letters on each of its sides. The main objective of this study is to find out the optimal number of letter cubes while maintaining the overall coverage. Comprehensive experiments on 12 datasets (from low-resource and high-resource languages) incorporating morphological features were conducted to form 3–5-letter words using 7–8 cubes and a special case of forming 6–7-letter words using 8–9 cubes. Experimental evaluations show that the ACG model achieved reasonably high results in terms of average total coverage, with 89.5% for 3–5-letter words using eight cubes and 79.7% for 6–7-letter words using nine cubes over 12 datasets. The ACG model obtained over 90% coverage for Uzbek, Turkish, English, Slovenian, Spanish, French, and Malaysian when constructing 3–5-letter words using eight cubes. Full article

Situation types can be viewed as the foundation of representation of sentence meaning. Noting that situation types cannot be determined by verbs alone, recent studies often focus on situation type prediction in terms of the combination of different linguistic constituents at the sentence level instead of lexically marked situation types. However, in languages with a fully marked aspectual system, such as Mandarin Chinese, such an approach may miss the opportunity of leveraging lexical aspects as well as other distribution-based lexical cues of event types. Currently, there is a lack of resources and methods for the identification and validation of the lexical aspect, and this issue is particularly severe for Chinese. From a computational linguistics perspective, the main reason for this shortage stems from the absence of a verified lexical aspect classification system, and consequently, a gold-standard dataset annotated according to this classification system. Additionally, owing to the lack of such a high-quality dataset, it remains unclear whether semantic models, including large general-purpose language models, can actually capture this important yet complex semantic information. As a result, the true realization of lexical aspect analysis cannot be achieved. To address these two problems, this paper sets out two objectives. First, we aim to construct a high-quality lexical aspect dataset. Since the classification of the lexical aspect depends on how it interacts with aspectual markers, we establish a scientific classification and data construction process through the selection of vocabulary items, the compilation of co-occurrence frequency matrices, and hierarchical clustering. Second, based on the constructed dataset, we separately evaluate the ability of linguistic features and large language model word embeddings to identify lexical aspect categories in order to (1) verify the capacity of semantic models to infer complex semantics and (2) achieve high-accuracy prediction of lexical aspects. Our final classification accuracy is 72.05%, representing the best result reported thus far. Full article

Background/Objectives: Although specific language impairment (SLI) was thought to be a language impairment, recent studies suggest that it is also associated with domain-general and nonverbal deficits such as deficits in nonverbal working memory, visual short-term memory, executive functions, etc. This study aimed to examine if applied visual strategy when copying the Rey–Osterrieth complex figure (ROCF) correlates with language abilities in children with SLI. Methods: The sample consisted of 37 children diagnosed with SLI, divided into two groups based on the strategy used when copying ROCF. We used ROCF to assess perceptual organization and planning, and the Peabody Picture Vocabulary Test, Boston Naming Test, Token Test, Grammatical Judgment, The Children’s Grammar, and Global Articulation Test for language measurement. Univariate ANOVA was used for statistical analysis. Results: The results indicate that children who used a more mature strategy when copying ROCF achieved better results on tests used to assess grammar and articulation status. Conclusions: These results support the conclusion that there are neurocognitive mechanisms underlying both grammatical and visuospatial deficits. The obtained results suggest the importance of examining visual and visuospatial functions in children with SLI and the need for more comprehensive treatment of those children. Full article