arXiv：cs.CL· Sangpil Youm, Annabel Stocks Natalias, Hayden Heninger, Leah Jones, Xiaoyang Jin, Xiaoya Zhang, Bonnie Dorr·· 13 小时前
REFLECT：角色感知的 Transformer 架构用于检测情感、情绪、礼貌与正式度
REFLECT: Role-Aware Detection of Sentiment, Emotion, Politeness, and Formality
AI 导读
研究者提出 REFLECT，一种角色感知的 Transformer 架构，将情感、情绪、礼貌与正式度（SEPF）四个维度映射到语义角色标注（SRL）配置并融入自注意力机制。在四个 benchmark 数据集上，该框架在情绪、礼貌与正式度检测上相较 BERT 类基线取得统计显著提升，情感维度提升则不显著。在真实心理健康数据上，该方法同时改善了预测性能与模型可追溯性。
正文
Abstract:Detecting communicative meaning in dialogue requires modeling not only lexical content but also the participant-role structures through which sentiment, emotion, politeness, and formality (SEPF) are expressed. Existing approaches rely on contextual language representations while leaving semantic roles implicit. We introduce a role-aware transformer architecture that maps the four SEPF dimensions to theory-grounded Semantic Role Labeling (SRL) configurations, incorporating these configurations directly into the transformer's self-attention mechanism. Role-aware attention models non-directional internal states (sentiment and emotion), while directional role-aware attention captures initiator-to-recipient relations for external cues (politeness and formality). The resulting role-aware representations are fused with contextual embeddings through a learned gate that adaptively weights how much role information each input contributes, rather than appending semantic roles as an auxiliary feature vector. Across four benchmark datasets, the framework yields statistically reliable gains over strong BERT-based baselines for emotion, politeness, and formality, with gains concentrated in theoretically predicted cases such as low-frequency, complex emotions and highly polite expressions; sentiment improvements are marginal and non-significant, suggesting that sentiment is conveyed more through lexical choice than participant-role structure. Additional evaluation on real-world data demonstrates that the framework improves both predictive performance and model traceability. These results demonstrate that linguistically grounded modifications to transformer self-attention improve the detection of communicative meaning, generalize beyond benchmark datasets to real-world mental-health data, and yield traceable, role-grounded explanations that extend beyond predictive performance to interpretability.
| Comments: | 9 pages, 2 figures |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.13797 [cs.CL] |
| (or arXiv:2610.13797v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13797 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sangpil Youm [view email]
[v1]
Fri, 9 Oct 2026 16:10:25 UTC (2,172 KB)
来源：arXiv：cs.CL · arxiv.org