Relation-Aware Collaborative Learning for Unified Aspect-Based Sentiment Analysis
Relation-Aware Collaborative Learning for Unified Aspect-Based Sentiment Analysis
复制标题
DOI：
10.18653/v1/2020.acl-main.340
复制
发表时间：
2020-07
期刊：
影响因子：
--
通讯作者：
Zhuang Chen-;T. Qian
中科院分区：
文献类型：
--
作者：
Zhuang Chen-;T. Qian
基于情感分析的情感分析（ABSA）涉及三个子任务，即，方面术语提取、观点术语提取和方面级情感分类。大多数现有的研究只集中在这些子任务之一。最近的一些研究成功地尝试用一个统一的框架来解决完整的ABSA问题。然而，这三个子任务之间的互动关系仍然没有得到充分的开发。我们认为，这种关系编码不同的子任务之间的合作信号。例如，当意见术语是“美味”时，体术语必须是“食物”而不是“地方”。为了充分利用这些关系，我们提出了一个可感知的协作学习（RACL）框架，它允许子任务协调工作，通过多任务学习和关系传播机制，在一个堆叠的多层网络。在三个真实世界数据集上的大量实验表明，RACL在完成ABSA任务方面明显优于最先进的方法。
Aspect-based sentiment analysis (ABSA) involves three subtasks, i.e., aspect term extraction, opinion term extraction, and aspect-level sentiment classification. Most existing studies focused on one of these subtasks only. Several recent researches made successful attempts to solve the complete ABSA problem with a unified framework. However, the interactive relations among three subtasks are still under-exploited. We argue that such relations encode collaborative signals between different subtasks. For example, when the opinion term is “delicious”, the aspect term must be “food” rather than “place”. In order to fully exploit these relations, we propose a Relation-Aware Collaborative Learning (RACL) framework which allows the subtasks to work coordinately via the multi-task learning and relation propagation mechanisms in a stacked multi-layer network. Extensive experiments on three real-world datasets demonstrate that RACL significantly outperforms the state-of-the-art methods for the complete ABSA task.