观察说话者：一种用于对话中情绪识别且具备情绪解耦的混合连续归因网络
Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement
AI总结：
本文提出混合连续归因网络HCAN，通过建模情绪连续性与情绪归因，并引入情绪认知损失缓解说话者建模过拟合，在多个数据集上取得领先性能。
摘要：
对话中的情绪识别（ERC）因其巨大的实际应用潜力而在自然语言处理领域引起了广泛关注。现有的ERC方法由于对上下文建模不足、对话关系捕捉模糊以及说话者建模中的过拟合，在实现跨场景泛化方面面临挑战。在本工作中，我们提出了一种混合连续归因网络（HCAN），从情绪连续性和情绪归因的角度来解决这些问题。具体而言，HCAN采用混合循环与基于注意力的模块来建模全局情绪连续性。然后，提出了一种新颖的情绪归因编码（EAE）来建模每个话语的内部和跨话语情绪归因。此外，为了增强模型在说话者建模中的鲁棒性并提高其在不同场景下的性能，提出了一种综合损失函数——情绪认知损失 $\mathcal{L}_{\rm EC}$，以缓解情绪漂移并克服模型对说话者建模的过拟合。我们的模型在三个数据集上取得了最先进的性能，证明了我们工作的优越性。还在三个基准上进行了广泛的对比实验和消融研究，为每个模块的有效性提供了证据。对泛化能力的进一步探索实验表明，EAE模块在我们的方法中具有即插即用的特性。
英文摘要：
Emotion Recognition in Conversation (ERC) has attracted widespread attention in the natural language processing field due to its enormous potential for practical applications. Existing ERC methods face challenges in achieving generalization to diverse scenarios due to insufficient modeling of context, ambiguous capture of dialogue relationships and overfitting in speaker modeling. In this work, we present a Hybrid Continuous Attributive Network (HCAN) to address these issues in the perspective of emotional continuation and emotional attribution. Specifically, HCAN adopts a hybrid recurrent and attention-based module to model global emotion continuity. Then a novel Emotional Attribution Encoding (EAE) is proposed to model intra- and inter-emotional attribution for each utterance. Moreover, aiming to enhance the robustness of the model in speaker modeling and improve its performance in different scenarios, A comprehensive loss function emotional cognitive loss $\mathcal{L}_{\rm EC}$ is proposed to alleviate emotional drift and overcome the overfitting of the model to speaker modeling. Our model achieves state-of-the-art performance on three datasets, demonstrating the superiority of our work. Another extensive comparative experiments and ablation studies on three benchmarks are conducted to provided evidence to support the efficacy of each module. Further exploration of generalization ability experiments shows the plug-and-play nature of the EAE module in our method.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
