用门控机制融合语义与结构特征，提升歌词分类准确率与可靠性
Synergistic Feature Fusion for Latent Lyrical Classification: A Gated Deep Learning Architecture
- 设计门控融合层，动态调节语义嵌入与结构特征
- 准确率98.94%，宏F1达98.94%，显著优于基线模型
- 校准性更好，适合对可信度要求高的歌词分析场景
本研究解决将复杂高维语义特征与简单可解释结构线索融合用于歌词内容分类的挑战。提出新型协同融合层（SFL）架构，利用门控机制调节句向量嵌入（Fdeep）并结合低维辅助特征（Fstruct）。任务基于UMAP降维后的歌词嵌入聚类重构为二分类：区分主导同质簇（类别0）与其他内容（类别1）。SFL模型达到0.9894的准确率和宏F1分数，优于采用特征拼接的随机森林基线（准确率0.9868）。关键优势在于更强的可靠性与校准性：预期校准误差降低93%（ECE=0.0035），对数损失减少2.5倍（Log Loss=0.0304），显著低于基线（ECE=0.0500；Log Loss=0.0772）。结果验证非线性门控优于简单拼接，确立SFL在复杂多模态歌词分析中的鲁棒性与可信性。
原文摘要 · Abstract (English)
This study addresses the challenge of integrating complex, high-dimensional deep semantic features with simple, interpretable structural cues for lyrical content classification. We introduce a novel Synergistic Fusion Layer (SFL) architecture, a deep learning model utilizing a gated mechanism to modulate Sentence-BERT embeddings (Fdeep) using low-dimensional auxiliary features (Fstruct). The task, derived from clustering UMAP-reduced lyrical embeddings, is reframed as binary classification, distinguishing a dominant, homogeneous cluster (Class 0) from all other content (Class 1). The SFL model achieved an accuracy of 0.9894 and a Macro F1 score of 0.9894, outperforming a comprehensive Random Forest (RF) baseline that used feature concatenation (Accuracy = 0.9868). Crucially, the SFL model demonstrated vastly superior reliability and calibration, exhibiting a 93% reduction in Expected Calibration Error (ECE = 0.0035) and a 2.5x lower Log Loss (0.0304) compared to the RF baseline (ECE = 0.0500; Log Loss = 0.0772). This performance validates the architectural hypothesis that non-linear gating is superior to simple feature concatenation, establishing the SFL model as a robust and trustworthy system for complex multimodal lyrical analysis.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。