A sentence may express sentiments on multiple aspects. When these aspects are associated with different sentiment polarities, a model's accuracy is often adversely affected. We observe that multiple aspects in such hard sentences are mostly expressed through multiple clauses, or formally known as elementary discourse units (EDUs), and one EDU tends to express a single aspect with unitary sentiment towards that aspect. In this paper, we propose to consider EDU boundaries in sentence modeling, with attentions at both word and EDU levels. Specifically, we highlight sentiment-bearing words in EDU through word-level sparse attention. Then at EDU level, we force the model to attend to the right EDU for the right aspect, by using EDU-level sparse attention and orthogonal regularization. Experiments on three benchmark datasets show that our simple EDU-Attention model outperforms state-of-the-art baselines. Because EDU can be automatically segmented with high accuracy, our model can be applied to sentences directly without the need of manual EDU boundary annotation.
翻译:当这些方面与不同情绪的两极性有关时,模型的准确性往往受到不利影响。我们观察到,这类强硬判决的多个方面大多表现为多个条款,或正式称为基本话语单元(EDUs),而一个EDU倾向于表达一个单一的方面,对这个方面有单一的情绪。在本文中,我们提议在文字和EDU两级都注意,在句子建模时考虑EDU的界限。具体地说,我们通过字数微弱的注意来突出EDU中含有情感的词句。然后,在EDU一级,我们通过使用EDU层次的微弱注意和或分层的正规化来迫使该模式在正确的方面关注EDU右方。关于三个基准数据集的实验表明,我们简单的EDU-注意力模型优于最先进的基线。由于EDU可以被自动分割,因此我们的模式可以直接用于判决,而不需要人工的EDU边界说明。