Decoupled variational autoencoder with interactive attention for affective text generation
Decoupled variational autoencoder with interactive attention for affective text generation
复制标题
DOI：
10.1016/j.engappai.2023.106447
复制
发表时间：
2023-08
期刊：
影响因子：
--
通讯作者：
Ruijun Chen;Jin Wang;Liang-Chih Yu;Xuejie Zhang
中科院分区：
文献类型：
--
作者：
Ruijun Chen;Jin Wang;Liang-Chih Yu;Xuejie Zhang
人工情感智能（AEI）是智能系统的一项重要能力。将情感状态表示为连续的情感强度可以实现比传统分类方法更细粒度的情感应用。通过使用情感强度，现有的变分自动编码器方法的主要挑战在于区分情感信息和语义信息。实际上，很难确保输入的训练文本不包含任何情感。如果用于文本生成的分离的潜在变量包含与分配的情感相冲突的情感特征，则生成的文本将是混乱的。因此，我们提出了一个解耦的变分自动编码器（VAE）与交互式注意力来解决这个问题。所提出的方法适用于情感抽取器从文本中提取的情感。然后，应用情感嵌入将强度映射到潜在空间中。为了提高情感嵌入的表达能力和解码器的性能，我们将情感文本的生成看作是一个去噪过程，在训练过程中设计了一种带噪采样策略，然后通过动态更新机制不断更新具有变分注意力的情感信息。在Yelp数据集和Amazon数据集上进行了大量的实验，实验结果表明，该方法在细粒度情感文本生成方面优于其他基于VAE的方法.
Artificial emotional intelligence (AEI) is an important ability for intelligent systems. Representing emotional states as a continuous sentiment intensity could achieve a more fine-grained sentiment application than traditional categorical approaches. By using sentiment intensity, the main challenge of the existing variational autoencoder methods lies in distinguishing emotional information from semantic information. Practically, it is difficult to ensure that the input training texts do not contain any sentiment. If the disentangled latent variable for text generation contains sentiment features that conflict with the assigned sentiment, the generated texts will be messy. Therefore, we propose a decoupled variational autoencoder (VAE) with interactive attention to solve this problem. The proposed method applies a sentiment decoupler to extract the sentiment from the text. Then, sentiment embeddings are applied to map the intensities into the latent space. To enhance the representation ability of sentiment embeddings and the performance of the decoder, we consider affective text generation as a process of denoising, design a noisy sampling strategy in training, and then continuously update the emotional information with variational attention through a dynamic update mechanism. Extensive experiments are conducted on the Yelp dataset and the Amazon dataset, and the experimental results show that our method outperforms other VAE-based methods in fine-grained affective text generation.