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

TL;DR

This paper introduces a Capsule Network-based model for semantic intent recognition in human-computer interaction, significantly improving accuracy and robustness over existing methods through hierarchical feature capture and dynamic routing.

Contribution

It presents a novel Capsule Network architecture with a margin-based loss for intent modeling, enhancing semantic feature representation and recognition accuracy.

Findings

Outperforms traditional and deep learning models in accuracy and F1-score

Effectively captures hierarchical semantic relationships

Demonstrates stability and improved performance with dynamic routing iterations

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.