Capsule Network-Based Semantic Intent Modeling for Human-Computer Interaction

• URL: http://arxiv.org/abs/2507.00540v1
• Date: Tue, 01 Jul 2025 08:00:12 GMT
• Title: Capsule Network-Based Semantic Intent Modeling for Human-Computer Interaction
• Authors: Shixiao Wang, Yifan Zhuang, Runsheng Zhang, Zhijun Song,
• Abstract summary: This paper proposes a user semantic intent modeling algorithm based on Capsule Networks.<n>It represents semantic features in input text through a vectorized capsule structure.<n>It uses a dynamic routing mechanism to transfer information across multiple capsule layers.
• Score: 2.3784833490134867
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper proposes a user semantic intent modeling algorithm based on Capsule Networks to address the problem of insufficient accuracy in intent recognition for human-computer interaction. The method represents semantic features in input text through a vectorized capsule structure. It uses a dynamic routing mechanism to transfer information across multiple capsule layers. This helps capture hierarchical relationships and part-whole structures between semantic entities more effectively. The model uses a convolutional feature extraction module as the low-level encoder. After generating initial semantic capsules, it forms high-level abstract intent representations through an iterative routing process. To further enhance performance, a margin-based mechanism is introduced into the loss function. This improves the model's ability to distinguish between intent classes. Experiments are conducted using a public natural language understanding dataset. Multiple mainstream models are used for comparison. Results show that the proposed model outperforms traditional methods and other deep learning structures in terms of accuracy, F1-score, and intent detection rate. The study also analyzes the effect of the number of dynamic routing iterations on model performance. A convergence curve of the loss function during training is provided. These results verify the stability and effectiveness of the proposed method in semantic modeling. Overall, this study presents a new structured modeling approach to improve intent recognition under complex semantic conditions.

Related papers

• Efficient Machine Unlearning via Influence Approximation [75.31015485113993]
  Influence-based unlearning has emerged as a prominent approach to estimate the impact of individual training samples on model parameters without retraining.<n>This paper establishes a theoretical link between memorizing (incremental learning) and forgetting (unlearning)<n>We introduce the Influence Approximation Unlearning algorithm for efficient machine unlearning from the incremental perspective.
  arXiv  Detail & Related papers  (2025-07-31T05:34:27Z)
• Neural Network Reprogrammability: A Unified Theme on Model Reprogramming, Prompt Tuning, and Prompt Instruction [55.914891182214475]
  We introduce neural network reprogrammability as a unifying framework for model adaptation.<n>We present a taxonomy that categorizes such information manipulation approaches across four key dimensions.<n>We also analyze remaining technical challenges and ethical considerations.
  arXiv  Detail & Related papers  (2025-06-05T05:42:27Z)
• Visual Explanation via Similar Feature Activation for Metric Learning [23.559106251249872]
  Class activation maps (CAM) have been extensively employed to explore the interpretability of softmax-based convolutional neural networks.<n>We propose a novel visual explanation method termed Similar Feature Activation Map (SFAM)<n>SFAM provides highly promising interpretable visual explanations for CNN models using Euclidean distance or cosine similarity as the similarity metric.
  arXiv  Detail & Related papers  (2025-06-02T13:14:37Z)
• Improving Network Interpretability via Explanation Consistency Evaluation [56.14036428778861]
  We propose a framework that acquires more explainable activation heatmaps and simultaneously increase the model performance. Specifically, our framework introduces a new metric, i.e., explanation consistency, to reweight the training samples adaptively in model learning. Our framework then promotes the model learning by paying closer attention to those training samples with a high difference in explanations.
  arXiv  Detail & Related papers  (2024-08-08T17:20:08Z)
• Decom--CAM: Tell Me What You See, In Details! Feature-Level Interpretation via Decomposition Class Activation Map [23.71680014689873]
  Class Activation Map (CAM) is widely used to interpret deep model predictions by highlighting object location. This paper proposes a new two-stage interpretability method called the Decomposition Class Activation Map (Decom-CAM) Our experiments demonstrate that the proposed Decom-CAM outperforms current state-of-the-art methods significantly.
  arXiv  Detail & Related papers  (2023-05-27T14:33:01Z)
• ContraFeat: Contrasting Deep Features for Semantic Discovery [102.4163768995288]
  StyleGAN has shown strong potential for disentangled semantic control. Existing semantic discovery methods on StyleGAN rely on manual selection of modified latent layers to obtain satisfactory manipulation results. We propose a model that automates this process and achieves state-of-the-art semantic discovery performance.
  arXiv  Detail & Related papers  (2022-12-14T15:22:13Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• SSA: Semantic Structure Aware Inference for Weakly Pixel-Wise Dense Predictions without Cost [36.27226683586425]
  The semantic structure aware inference (SSA) is proposed to explore the semantic structure information hidden in different stages of the CNN-based network to generate high-quality CAM in the model inference. The proposed method has the advantage of no parameters and does not need to be trained. Therefore, it can be applied to a wide range of weakly-supervised pixel-wise dense prediction tasks.
  arXiv  Detail & Related papers  (2021-11-05T11:07:21Z)
• Firearm Detection via Convolutional Neural Networks: Comparing a Semantic Segmentation Model Against End-to-End Solutions [68.8204255655161]
  Threat detection of weapons and aggressive behavior from live video can be used for rapid detection and prevention of potentially deadly incidents. One way for achieving this is through the use of artificial intelligence and, in particular, machine learning for image analysis. We compare a traditional monolithic end-to-end deep learning model and a previously proposed model based on an ensemble of simpler neural networks detecting fire-weapons via semantic segmentation.
  arXiv  Detail & Related papers  (2020-12-17T15:19:29Z)
• Eigen-CAM: Class Activation Map using Principal Components [1.2691047660244335]
  This paper builds on previous ideas to cope with the increasing demand for interpretable, robust, and transparent models. The proposed Eigen-CAM computes and visualizes the principle components of the learned features/representations from the convolutional layers.
  arXiv  Detail & Related papers  (2020-08-01T17:14:13Z)
• Autoencoding Pixies: Amortised Variational Inference with Graph Convolutions for Functional Distributional Semantics [12.640283469603355]
  Pixie Autoencoder augments the generative model of Functional Distributional Semantics with a graph-convolutional neural network to perform amortised variational inference.
  arXiv  Detail & Related papers  (2020-05-06T17:46:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.