A Multi-Branch Transformer-Enhanced Neural Framework for Joint Morphological Representation Learning

Morphological parsing is a fundamental task in natural language processing, particularly for morphologically rich languages where words encode complex grammatical and semantic information. This paper proposes a multi-branch Transformer-enhanced neural framework for joint morphological representation learning, designed to improve segmentation and classification accuracy by integrating complementary feature extraction mechanisms. The proposed architecture combines convolutional layers for capturing local morphological patterns, recurrent layers for modeling sequential dependencies, and Transformer-based self-attention for learning global contextual relationships. This hybrid design enables the model to generate robust and context-aware representations that enhance morphological understanding. The framework is trained using morphologically annotated datasets and evaluated using standard performance metrics, including F1-score and classification accuracy. Experimental results demonstrate that the proposed model significantly outperforms conventional and single-architecture baselines in both segmentation and morphological classification tasks. The learned representations exhibit strong discriminative capability, allowing accurate identification of morpheme boundaries and grammatical features. Furthermore, the model demonstrates stable convergence behavior and strong generalization performance across diverse linguistic conditions. These findings confirm the effectiveness of integrating multi-level contextual and structural feature extraction mechanisms, establishing the proposed framework as a robust and scalable solution for advanced morphological parsing and representation learning in modern natural language processing applications.