Abstract
Generating long and informative review text is a challenging natural language generation task. Previous work focuses on word-level generation, neglecting the importance of topical and syntactic characteristics from natural languages. In this paper, we propose a novel review generation model by characterizing an elaborately designed aspect-aware coarse-to-fine generation process. First, we model the aspect transitions to capture the overall content flow. Then, to generate a sentence, an aspect-aware sketch will be predicted using an aspect-aware decoder. Finally, another decoder fills in the semantic slots by generating corresponding words. Our approach is able to jointly utilize aspect semantics, syntactic sketch, and context information. Extensive experiments results have demonstrated the effectiveness of the proposed model.
Abstract (translated)
生成冗长且信息丰富的评论文本是一项具有挑战性的自然语言生成任务。以往的研究集中在词汇层面的生成，忽略了自然语言的主题和句法特征的重要性。本文通过描述一个精心设计的面向方面的粗到细生成过程，提出了一种新的回顾生成模型。首先，我们对方面转换进行建模，以捕获整个内容流。然后，为了生成一个句子，将使用一个方面感知解码器来预测一个方面感知草图。最后，另一个解码器通过生成相应的单词来填充语义槽。我们的方法能够联合使用方面语义、语法草图和上下文信息。大量的实验结果证明了该模型的有效性。
URL
https://arxiv.org/abs/1906.05667
