Semantic Model Research Articles

Mapping and modeling the semantic space of math concepts

Mathematics is an underexplored domain of human cognition. While many studies have focused on subsets of math concepts such as numbers, fractions, or geometric shapes, few have ventured beyond these elementary domains. Here, we attempted to map out the full space of math concepts and to answer two specific questions: can distributed semantic models, such a GloVe, provide a satisfactory fit to human semantic judgements in mathematics? And how does this fit vary with education? We first analyzed all of the French and English Wikipedia pages with math contents, and used a semi-automatic procedure to extract the 1000 most frequent math terms in both languages. In a second step, we collected extensive behavioral judgements of familiarity and semantic similarity between them. About half of the variance in human similarity judgements was explained by vector embeddings that attempt to capture latent semantic structures based on cooccurence statistics. Participants' self-reported level of education modulated familiarity and similarity, allowing us to create a partial hierarchy among high-level math concepts. Our results converge onto the proposal of a map of math space, organized as a database of math terms with information about their frequency, familiarity, grade of acquisition, and entanglement with other concepts.

QSIM: A Quantum-inspired hierarchical semantic interaction model for text classification

Semantic interaction modeling is a fundamental technology in natural language understanding that guides models to extract deep semantic information from text. Currently, the attention mechanism is one of the most effective techniques in semantic interaction modeling, which learns word-level attention representation by measuring the relevance between different words. However, the attention mechanism is limited to word-level semantic interaction, it cannot meet the needs of fine-grained interactive information for some text classification tasks. In recent years, quantum-inspired language modeling methods have successfully constructed quantized representations of language systems in Hilbert spaces, which use density matrices to achieve fine-grained semantic interaction modeling.This paper presents a Quantum-inspired hierarchical Semantic Interaction Model (QSIM), which follows the sememe-word-sentence language construction principle and utilizes quantum entanglement theory to capture hierarchical semantic interaction information in Hilbert space. Our work builds on the idea of the attention mechanism and extends it. Specifically, we explore the original semantic space from a quantum theory perspective and derive the core semantic space using the Schmidt decomposition technique, where: (1) Sememe is represented as the unit vector in the two-dimensional minimum semantic space; (2) Word is represented as reduced density matrices in the core semantic space, where Schmidt coefficients quantify sememe-level semantic interaction. Compared to density matrices, reduced density matrices capture fine-grained semantic interaction information with lower computational cost; (3) Sentence is represented as quantum superposition states of words, and the degree of word-level semantic interaction is measured using entanglement entropy.To evaluate the model’s performance, we conducted experiments on 15 text classification datasets. The experimental results demonstrate that our model is superior to classical neural network models and traditional quantum-inspired language models. Furthermore, the experiment also confirms two distinct advantages of QISM: (1) flexibility, as it can be integrated into various mainstream neural network text classification architectures; and (2) practicability, as it alleviates the problem of parameter growth inherent in density matrix calculation in quantum language model.

An embedded computational framework of memory: Accounting for the influence of semantic information in verbal short-term memory

We introduce the Embedded Computational Framework of Memory (eCFM), a model that integrates structured semantic word representations with an instance-based memory model to account for the influence of semantic information in verbal short-term memory. The eCFM combines principles from the episodic MINERVA 2 model and the semantic Latent Semantic Analysis model. After reviewing how semantic information impacts verbal short-term memory performance, we demonstrate eCFM’s ability to reconcile various phenomena within a common computational framework. Our model captures key findings, such as the influence of semantic information in serial recall, its reduction in serial reconstruction, and the impact of task difficulty on semantic information. In five experiments, we tested predictions derived from the eCFM. Experiments 1 and 2 manipulated list organization, with Experiment 1 using alternating lists of related or unrelated words and Experiment 2 using blocked lists. Experiment 3 varied presentation rates, Experiment 4 revisited the detrimental effect of semantic information on order information, and Experiment 5 explored false recall. We found that semantic information interacts with list composition, presentation rate affects the magnitude of its influence, and semantic information impacts order information contrary to the dominant view. Additionally, increasing the number of related study words to a non-studied semantic lure boosts false recall. The eCFM captured these findings as well as memory at the item level. Our demonstration provides insight into the cognitive mechanisms underlying verbal short-term memory and the interplay of semantic and episodic memory processes in recall.

Enhancing bilingual lexicon induction via harnessing polysemous words

Bilingual Lexicon Induction (BLI) aims to induce word translation pairs across different languages. We find there is a large proportion of polysemous words in the dataset used by BLI, which impacts the quality of the induced translation pairs. In particular, the mainstream BLI models map two monolingual word embeddings (WEs) into a shared space and regard the closest cross-lingual words as translation pairs. However, when a word has multiple translations, it becomes challenging to ensure that the polysemous word is the closest neighbor to all its translations. Based on the analysis of polysemy, we propose a simple yet effective method by harnessing polysemous words to enhance BLI. We first detect polysemous words in the seed lexicons and filter their multiple translations by comparing their semantic similarities. Therefore, a refined seed lexicon mitigates the confusion caused by translations with divergent semantics for the BLI model. Moreover, in scenarios where only single translations are available in the seed lexicon, we propose to employ a Large Language Model (LLM) to acquire monolingual synonyms, thereby refining the structure of the seed lexicon more effectively. On benchmark BLI datasets, our method demonstrates superior performance compared to five state-of-the-art (SOTA) baseline systems across almost all experimental language pairs, encompassing both sides of three similar language pairs and three distant language pairs.

When segment anything model meets inventorying of roadway assets

Automating the identification, localization, and monitoring of roadway assets distributed widely in the roadway network is critical for the traffic management system. It can efficiently provide up-to-date information in supporting transportation asset management. Collecting videos with vehicle-mounted cameras and processing the data with computer vision-based deep learning methods is garnering increased attention from transportation agencies. While promising, challenges arise due to the lack of high-quality annotations for roadway assets in images, difficulties in identifying these assets, and limited solutions. The Segment Anything Model (SAM), a visual foundation model, demonstrates robust zero-shot capability for general image segmentation under various prompts. This study evaluates SAM’s applicability and efficiency in extracting roadway assets from images. Specifically, it examines the impacts of model size and prompt quality on SAM’s performance in segmenting roadway assets. Five state-of-the-art semantic segmentation models are trained and compared with SAM. Results show that a lightweight SAM with human-rendered prompts outperforms the five semantic segmentation models. Based on the evaluation results, future work will explore incorporating SAM into transportation asset management applications, promoting collaboration between human experts and artificial intelligence.

Prototype-Based Semantic Segmentation.

Deep learning based semantic segmentation solutions have yielded compelling results over the preceding decade. They encompass diverse network architectures (FCN based or attention based), along with various mask decoding schemes (parametric softmax based or pixel-query based). Despite the divergence, they can be grouped within a unified framework by interpreting the softmax weights or query vectors as learnable class prototypes. In light of this prototype view, we reveal inherent limitations within the parametric segmentation regime, and accordingly develop a nonparametric alternative based on non-learnable prototypes. In contrast to previous approaches that entail the learning of a single weight/query vector per class in a fully parametric manner, our approach represents each class as a set of non-learnable prototypes, relying solely upon the mean features of training pixels within that class. The pixel-wise prediction is thus achieved by nonparametric nearest prototype retrieving. This allows our model to directly shape the pixel embedding space by optimizing the arrangement between embedded pixels and anchored prototypes. It is able to accommodate an arbitrary number of classes with a constant number of learnable parameters. Through empirical evaluation with FCN based and Transformer based segmentation models (i.e., HRNet, Swin, SegFormer, Mask2Former) and backbones (i.e., ResNet, HRNet, Swin, MiT), our nonparametric framework shows superior performance on standard segmentation datasets (i.e., ADE20 K, Cityscapes, COCO-Stuff), as well as in large-vocabulary semantic segmentation scenarios. We expect that this study will provoke a rethink of the current de facto semantic segmentation model design.

A semantic segmentation network based on CNN and Swin transformer for landslide detection

Abstract To address the issues of poor object localization, difficulty in object recognition, and inadequate segmentation performance of CNN-based semantic segmentation methods in landslide detection, a semantic segmentation model based on the Swin transformer and ResUNet architectures for landslide detection in remote sensing images is proposed in this paper. This method combines the global feature capabilities of the Swin transformer with the local feature extraction abilities of CNN and integrates our proposed RCCT module for landslide segmentation in remote sensing images. We apply this model to the identification and extraction of landslide disasters in Menyuan County and the Sanjiangyuan region of Qinghai Province, China, achieving a promising F1 Score of 81.91. Furthermore, we conducted a comprehensive evaluation of our proposed model on the BiJie Landslide dataset in comparison to four recently developed methods for landslide recognition. The experimental findings indicate the superior performance and effectiveness of our model over the comparative approaches.

Improved semantic segmentation method for weld penetration prediction of TIG welding with dual ellipsoid heat source

TIG welding is a manufacturing process that uses argon as a shielding gas and tungsten as an electrode to join metals at high temperatures. The weld penetration is the key to determining the quality of the weld. However, the lack of sensing technology makes weld penetration difficult to predict, which imposes a major challenge to process stability and weld quality. To address this challenge, a semantic segmentation-based approach for calibrating the weld penetration prediction model under dual ellipsoidal heat source is proposed to improve the prediction accuracy. To realize this, a semantic segmentation model Self-Attention-Structural-Reparameterization-BiSeNet (SASR-BiSeNet) is built for molten pool parameter extraction. The model introduces a self-attention mechanism as an enhancement to the convolution module. Meanwhile, the RepVGG-style structural reparameterization design decouples the training-time and inference-time architectures. Further, a mask feature extraction method is designed to obtain the calibration parameters of the molten pool and to correct the prediction model. The accuracy of the calibrated prediction model is verified by welding experiments using 304L steel materials on a robotic welding system. The results show that the maximum Mean Intersection over Union (mIoU) of the SASR-BiSeNet is 92.51 %, which is a 13.87 % improvement compared to the BiSeNet, and the maximum depth of molten pool error decreasing from 16.59 % to 9.84 %. This method can improve the precision of welding penetration control and plays an important role in promoting welding intelligence.

Multimodal dual perception fusion framework for multimodal affective analysis

The misuse of social platforms and the difficulty in regulating post contents have culminated in a surge of negative sentiments, sarcasms, and the rampant spread of fake news. In response, Multimodal sentiment analysis, sarcasm detection and fake news detection based on image and text have attracted considerable attention recently. Due to that these areas share semantic and sentiment features and confront related fusion challenges in deciphering complex human expressions across different modalities, integrating these multimodal classification tasks that share commonalities across different scenarios into a unified framework is expected to simplify research in sentiment analysis, and enhance the effectiveness of classification tasks involving both semantic and sentiment modeling. Therefore, we consider integral components of a broader spectrum of research known as multimodal affective analysis towards semantics and sentiment, and propose a novel multimodal dual perception fusion framework (MDPF). Specifically, MDPF contains three core procedures: (1) Generating bootstrapping language-image Knowledge to enrich origin modality space, and utilizing cross-modal contrastive learning for aligning text and image modalities to understand underlying semantics and interactions. (2) Designing dynamic connective mechanism to adaptively match image-text pairs and jointly employing gaussian-weighted distribution to intensify semantic sequences. (3) Constructing a cross-modal graph to preserve the structured information of both image and text data and share information between modalities, while introducing sentiment knowledge to refine the edge weights of the graph to capture cross-modal sentiment interaction. We evaluate MDPF on three publicly available datasets across three tasks, and the empirical results demonstrate the superiority of our proposed model.

RS-SLAM: real time semantic slam with driverless car using LiDAR-camera-IMU sensing

Abstract Accurate and robust Simultaneous Localization and Mapping (SLAM) technology is a critical component of driverless cars, and semantic information plays a vital role in their analysis and understanding of the scene. In the actual scene, the moving object will produce the shadow phenomenon in the mapping process. The positioning accuracy and mapping effect will be affected. Therefore, we propose a semantic SLAM framework combining LiDAR, IMU, and camera, which includes a semantic fusion front-end odometry module and a closed-loop back-end optimization module based on semantic information. An improved image semantic segmentation algorithm based on Deeplabv3+ is designed to enhance the performance of the image semantic segmentation model by replacing the backbone network and introducing an attention mechanism to ensure the accuracy of point cloud segmentation. Dynamic objects are detected and eliminated by calculating the similarity score of semantic labels. A loop closure detection method based on semantic information is proposed to detect key semantic features and use threshold range detection and point cloud re-matching to establish the correct loop closure detection, and finally reduce the global cumulative error and improve the global trajectory accuracy using graph optimization to ultimately obtain the global motion trajectory and realize the construction of 3D semantic maps. We evaluated it on the KITTI dataset and collected a dataset for evaluation by ourselves, which includes four different sequences. The results show that the proposed framework has good positioning accuracy and mapping effect in large-scale urban road environments.

Detection of artificial spots in fundus images using modified U-Net based semantic segmentation

Today, deep learning algorithms are playing a very crucial role in the initial stage diagnosis of several fundus diseases like glaucoma, hypertension, and diabetic retinopathy. Lots of research is going on in this area now-a-days. During the acquisition of fundus images some artificial spots (e.g. because of the device itself, dust particles in the surroundings) have been added in captured images. In this paper, artificial spots in the fundus images that are generated due to the non-standardized conditions of scanning devices, are detected with the help of a newly proposed modified UNet (mU-Net) semantic segmentation model. Initially, preprocessing methods such as Gaussian blur, thresholding, and Hough transform have been used to create artificial spots. Now these preprocessed images have been used for training the proposed model. To make the proposed model more effective, the following modifications like, Regularization techniques (early stopping, greater weight decay, and Adam optimizer), decay learning rate scheduler, categorical cross-entropy loss function, and a significant number of filters have been modified in simple U-Net model. Apart from these mentioned modifications in the base U-Net model, a feature injecting module (FIM) has been added between the expansion and the contraction section of the simple U-Net model. FIM adds the features of the input image at the time of up-sampling. The addition of FIM to a simple U-Net model improves the detection of artificial spots and enhances the performance of the model. The mU-Net has been compared with other models, namely simple U-Net, V-Net, UNet++, ResUnet-a, WideU-Net, and Swin-Unet. The Friedman test that has been conducted on IOU, DICE, MAE, PSNR, and SSIM scores, found that mU-Net balances evaluation metrics well. It appears that the nonparametric Friedman test will improve reproducibility by demonstrating statistical significance. The IOU, DICE, MAE, PSNR, and SSIM scores of the proposed model indicate superior performance as compared to other models.

A General Boolean Semantic Modelling Approach for Complex and Intelligent Industrial Systems in the Framework of DES

A General Boolean Semantic Modelling Approach for Complex and Intelligent Industrial Systems in the Framework of DES

Real-time segmentation of biliary structure in pure laparoscopic donor hepatectomy

Pure laparoscopic donor hepatectomy (PLDH) has become a standard practice for living donor liver transplantation in expert centers. Accurate understanding of biliary structures is crucial during PLDH to minimize the risk of complications. This study aims to develop a deep learning-based segmentation model for real-time identification of biliary structures, assisting surgeons in determining the optimal transection site during PLDH. A single-institution retrospective feasibility analysis was conducted on 30 intraoperative videos of PLDH. All videos were selected for their use of the indocyanine green near-infrared fluorescence technique to identify biliary structure. From the analysis, 10 representative frames were extracted from each video specifically during the bile duct division phase, resulting in 300 frames. These frames underwent pixel-wise annotation to identify biliary structures and the transection site. A segmentation task was then performed using a DeepLabV3+ algorithm, equipped with a ResNet50 encoder, focusing on the bile duct (BD) and anterior wall (AW) for transection. The model’s performance was evaluated using the dice similarity coefficient (DSC). The model predicted biliary structures with a mean DSC of 0.728 ± 0.01 for BD and 0.429 ± 0.06 for AW. Inference was performed at a speed of 15.3 frames per second, demonstrating the feasibility of real-time recognition of anatomical structures during surgery. The deep learning-based semantic segmentation model exhibited promising performance in identifying biliary structures during PLDH. Future studies should focus on validating the clinical utility and generalizability of the model and comparing its efficacy with current gold standard practices to better evaluate its potential clinical applications.

An artificial intelligence-assisted digital microfluidic system for multistate droplet control

Digital microfluidics (DMF) is a versatile technique for parallel and field-programmable control of individual droplets. Given the high level of variability in droplet manipulation, it is essential to establish self-adaptive and intelligent control methods for DMF systems that are informed by the transient state of droplets and their interactions. However, most related studies focus on droplet localization and shape recognition. In this study, we develop the AI-assisted DMF framework μDropAI for multistate droplet control on the basis of droplet morphology. The semantic segmentation model is integrated into our custom-designed DMF system to recognize the droplet states and their interactions for feedback control with a state machine. The proposed model has strong flexibility and can recognize droplets of different colors and shapes with an error rate of less than 0.63%; it enables control of droplets without user intervention. The coefficient of variation (CV) of the volumes of split droplets can be limited to 2.74%, which is lower than the CV of traditional dispensed droplets, contributing to an improvement in the precision of volume control for droplet splitting. The proposed system inspires the development of semantic-driven DMF systems that can interface with multimodal large language models (MLLMs) for fully automatic control.

Energy system optimization based on fuzzy decision support system and unstructured data

To address the complex challenges in energy systems, this study proposes a novel optimization framework that integrates fuzzy decision support and unstructured data processing technologies. This framework aims to improve efficiency, reduce costs, decrease environmental impact, increase system flexibility, and enhance user satisfaction, thereby promoting sustainable development in the energy industry. The framework combines the innovative Energy Semantic Mapping Model (ESMM) and the advanced deep learning architecture ResNet to process textual and visual data effectively. ESMM enables accurate prediction of energy demand, while ResNet significantly reduces equipment maintenance costs and improves energy distribution efficiency. These advancements are critical as they address the limitations of existing approaches in handling large-scale unstructured data and making informed decisions under uncertainty. The Environmental Impact Assessment (EIA) confirms the model's effectiveness in reducing carbon emissions. A comprehensive economic analysis demonstrates substantial cost savings in energy procurement and operations and maintenance, with overall savings exceeding 25%. Enhanced user satisfaction and reduced system response times further validate the practical utility of the proposed approach. Additionally, a genetic algorithm is used to optimize the fuzzy rule base, enhancing the robustness and adaptability of the model. Experimental results show superior performance compared to traditional systems, providing strong empirical evidence for the intelligent transformation of energy systems. This research contributes to the field by offering a more sophisticated and flexible solution for managing energy systems, particularly in terms of leveraging unstructured data and improving decision-making processes.

A Multi-Scale Content-Structure Feature Extraction Network Applied to Gully Extraction

Black soil is a precious soil resource, yet it is severely affected by gully erosion, which is one of the most serious manifestations of land degradation. The determination of the location and shape of gullies is crucial for the work of gully erosion control. Traditional field measurement methods consume a large amount of human resources, so it is of great significance to use artificial intelligence techniques to automatically extract gullies from satellite remote sensing images. This study obtained the gully distribution map of the southwestern region of the Dahe Bay Farm in Inner Mongolia through field investigation and measurement and created a gully remote sensing dataset. We designed a multi-scale content structure feature extraction network to analyze remote sensing images and achieve automatic gully extraction. The multi-layer information obtained through the resnet34 network is input into the multi-scale structure extraction module and the multi-scale content extraction module designed by us, respectively, obtained richer intrinsic information about the image. We designed a structure content fusion network to further fuse structural features and content features and improve the depth of the model’s understanding of the image. Finally, we designed a muti-scale feature fusion module to further fuse low-level and high-level information, enhance the comprehensive understanding of the model, and improve the ability to extract gullies. The experimental results show that the multi-scale content structure feature extraction network can effectively avoid the interference of complex backgrounds in satellite remote sensing images. Compared with the classic semantic segmentation models, DeepLabV3+, PSPNet, and UNet, our model achieved the best results in several evaluation metrics, the F1 score, recall rate, and intersection over union (IoU), with an F1 score of 0.745, a recall of 0.777, and an IoU of 0.586. These results proved that our method is a highly automated and reliable method for extracting gullies from satellite remote sensing images, which simplifies the process of gully extraction and provides us with an accurate guide to locate the location of gullies, analyze the shape of gullies, and then provide accurate guidance for gully management.

Exploring multi-granularity contextual semantics for fully inductive knowledge graph completion

Fully inductive knowledge graph completion (KGC) aims to predict triplets involving both unseen entities and relations. Recent several approaches transform paths between entities into descriptions and modeling semantic correlations between paths using pre-trained language models (PLMs), have emerged as a promising solution for fully inductive reasoning. However, these methods often adopt a simplistic concatenation strategy for path-to-sentence transformation, which impedes PLMs’ ability to capture subtle nuances in context, resulting in sub-optimal path context embeddings. Furthermore, they ignore the high-order semantics underlying the complete context, which can provide richer information for inductive reasoning. To address these issues, we propose a Multi-Granularity Contextual Semantic (MGCS) modeling framework, utilizing a Path Modeling Network (PMN) and a Subgraph Modeling Network (SMN) to extract two granularity levels of contextual semantics from single paths and complete subgraphs, for fully inductive KGC. The PMN extracts paths between head and tail entities and employs reasoning patterns from similar cases to filter out unreliable paths. Then two innovative path conversion strategies are designed to significantly enhance the pre-trained language model’s understanding of specific path contexts. The SMN employs a neighbor interactive graph neural network to extract high-order semantics from the complete subgraph context with a concept-enhanced relation encoding, and optimizes it through a contrastive learning method. Finally, the confidence of the triples is evaluated from the perspective of global complete context by comparing the semantics between the subgraphs surrounding the target triplet and the subgraphs surrounding similar cases. Experimental results on benchmark datasets demonstrate the effectiveness of MGCS.

Learning precise segmentation of neurofibrillary tangles from rapid manual point annotations.

Accumulation of abnormal tau protein into neurofibrillary tangles (NFTs) is a pathologic hallmark of Alzheimer disease (AD). Accurate detection of NFTs in tissue samples can reveal relationships with clinical, demographic, and genetic features through deep phenotyping. However, expert manual analysis is time-consuming, subject to observer variability, and cannot handle the data amounts generated by modern imaging. We present a scalable, open-source, deep-learning approach to quantify NFT burden in digital whole slide images (WSIs) of post-mortem human brain tissue. To achieve this, we developed a method to generate detailed NFT boundaries directly from single-point-per-NFT annotations. We then trained a semantic segmentation model on 45 annotated 2400μm by 1200μm regions of interest (ROIs) selected from 15 unique temporal cortex WSIs of AD cases from three institutions (University of California (UC)-Davis, UC-San Diego, and Columbia University). Segmenting NFTs at the single-pixel level, the model achieved an area under the receiver operating characteristic of 0.832 and an F1 of 0.527 (196-fold over random) on a held-out test set of 664 NFTs from 20 ROIs (7 WSIs). We compared this to deep object detection, which achieved comparable but coarser-grained performance that was 60% faster. The segmentation and object detection models correlated well with expert semi-quantitative scores at the whole-slide level (Spearman's rho ρ=0.654 (p=6.50e-5) and ρ=0.513 (p=3.18e-3), respectively). We openly release this multi-institution deep-learning pipeline to provide detailed NFT spatial distribution and morphology analysis capability at a scale otherwise infeasible by manual assessment.

Multilayer spatial-spectral segmentation network for detecting AFB1

Aflatoxin, a toxin produced by Aspergillus flavus, is commonly found in peanuts and poses a significant threat to human health. In this paper, we propose an adjustable Mul-U-Net model, capable of learning both spectral and spatial information in parallel, facilitating rapid detection of aflatoxins by adjusting the number of central spatial U units. First, AFB1 was semantically segmented by inputting hyperspectral image cubes into six semantic segmentation models: Mul-U-Net, U-Net, FCN, SegNet, CNN, and RefineNet. Experimental results demonstrate that Mul-U-Net outperformed the other models, achieving an overall accuracy of 95.64 % and an RMSE of 0.2079. We further examined the influence of different spatial U units on model performance and found that the optimal spatial U count matched the number of labels. In the aflatoxin dataset, the Mul-2 U-Net model achieved the highest accuracy of 96.12 %. Further validation on the Indian Pines and Pavia University datasets showed that Mul-16 U-Net and Mul-9 U-Net achieved the highest accuracies of 98.12 % and 98.01 %, respectively. This study presents a robust, high-performance, and tunable Mul-U-Net semantic segmentation network, offering a valuable new approach for the identification of aflatoxins in peanuts.

Analisis Semantik dan Penggunaan Media Canva pada Pembuatan Slogan di Kelas VIII SMP Darussalam Medan

This research is entitled "Semantic Analysis and Use of Canva Media in Making Slogans in Class VIII of Darussalam Middle School, Medan". This research examines semantic analysis and the use of Canva media in the process of creating slogans by class VIII students at Darussalam Middle School, Medan. The main aim is to reveal the semantic meaning of the slogans produced by students. This research uses a descriptive method with a semantic approach, referring to Verhaar's semantic model, which involves analysis of lexical, grammatical and conceptual meaning. The research found three types of slogans created by students, namely health/hygiene slogans, education slogans, and motivation/advice slogans, each consisting of five slogans. Canva media has proven to be effective in helping students integrate visual and verbal elements, thereby increasing their creativity and understanding of the meaning of the slogans produced. Apart from that, using Canva also increases students' enthusiasm for learning through more interesting visual interactions. This research suggests that canva be used as a tool in teaching Indonesian, especially in material related to making slogans and understanding semantics. Lexical meaning analysis is carried out based on the meaning of words in the KBBI, grammatical meaning is analyzed through a morphophonemic process, and conceptual meaning is evaluated according to the relevant context