Similarity-Based Intent Detection Using an Enhanced Siamese Network

In Natural Language Understanding (NLU), intent detection is crucial for improving human-computer interaction. However, traditional supervised learning models rely heavily on large annotated datasets, limiting their effectiveness in low-resource scenarios. Siamese networks, which are effective at learning similarity-based representations, offer a potential solution through simpler architectures. However, they often rely on triplet loss, which can be complex to optimize. This study introduces a similarity-based intent detection model using an enhanced Siamese network to address these challenges. Our model employs Manhattan, Euclidean, and Cosine similarity metrics combined with a fusion layer to improve intent classification accuracy. We evaluated the model on the Airline Travel Information System (ATIS) and SNIPS datasets and demonstrated its superiority over state-of-the-art methods. The results highlight significant accuracy gains while maintaining computational efficiency, making it a robust solution for real-world dialog systems.