Structured sentiment analysis, which aims to extract the complex semantic structures such as holders, expressions, targets, and polarities, has obtained widespread attention from both industry and academia. Unfortunately, the existing structured sentiment analysis datasets refer to a few languages and are relatively small, limiting neural network models' performance. In this paper, we focus on the cross-lingual structured sentiment analysis task, which aims to transfer the knowledge from the source language to the target one. Notably, we propose a Knowledge-Enhanced Adversarial Model (\texttt{KEAM}) with both implicit distributed and explicit structural knowledge to enhance the cross-lingual transfer. First, we design an adversarial embedding adapter for learning an informative and robust representation by capturing implicit semantic information from diverse multi-lingual embeddings adaptively. Then, we propose a syntax GCN encoder to transfer the explicit semantic information (e.g., universal dependency tree) among multiple languages. We conduct experiments on five datasets and compare \texttt{KEAM} with both the supervised and unsupervised methods. The extensive experimental results show that our \texttt{KEAM} model outperforms all the unsupervised baselines in various metrics.
翻译:结构性情绪分析旨在提取持有者、表达方式、目标和两极性等复杂的语义结构,得到了产业界和学术界的广泛关注。 不幸的是,现有的结构化情绪分析数据集指的是少数语言,相对小,限制了神经网络模型的性能。 在本文中,我们侧重于跨语言结构化情绪分析任务,目的是将知识从源语言转移到目标语言。 值得注意的是,我们提议了一个知识强化的对立模型(\ textt{KEAM}),既具有隐含分布式,又具有明确的结构性知识,以加强跨语言的传输。首先,我们设计了一个对称性情感分析数据集嵌入器,通过从多种语言的多语言嵌入中获取隐含的语义信息,从而学习信息性和强健的代表性。然后,我们提出一个语义化的GCN编码器,以便在多种语言中传输明确的语义信息(例如普遍依赖树)。我们在五个数据集上进行实验,并将\ textt{KEAM}与不受监督的模型和未监督的方法进行比较。 广泛的实验性结果显示我们的各种基准模型中的所有模型都显示。