论文标题
从情感注释到情感通过话语的预测
From Sentiment Annotations to Sentiment Prediction through Discourse Augmentation
论文作者
论文摘要
情感分析，特别是对于长文档，可能需要捕获复杂语言学结构的方法。为了适应这一点，我们提出了一个新颖的框架，以利用与任务相关的话语进行情感分析的任务。更具体地说，我们将大规模的，情感依赖性的巨型树库与一种新型的神经体系结构相结合，以基于混合TreelstM层次等级注意模型，以进行情感预测。实验表明，我们使用与情感相关的话语增强进行情感预测的框架可以增强长文档的整体绩效，甚至超越了以前的方法，使用了经过良好的人类注释数据培训的良好的话语解析器。我们表明，根据文档的长度，一种简单的合奏方法可以选择性地使用话语进一步提高性能。
Sentiment analysis, especially for long documents, plausibly requires methods capturing complex linguistics structures. To accommodate this, we propose a novel framework to exploit task-related discourse for the task of sentiment analysis. More specifically, we are combining the large-scale, sentiment-dependent MEGA-DT treebank with a novel neural architecture for sentiment prediction, based on a hybrid TreeLSTM hierarchical attention model. Experiments show that our framework using sentiment-related discourse augmentations for sentiment prediction enhances the overall performance for long documents, even beyond previous approaches using well-established discourse parsers trained on human annotated data. We show that a simple ensemble approach can further enhance performance by selectively using discourse, depending on the document length.
