论文标题
方面控制的神经论点一代
Aspect-Controlled Neural Argument Generation
论文作者
论文摘要
我们依靠日常生活中的论点来表达我们的观点并以证据为基础，从而使它们更具说服力。但是，寻找和制定论点可能具有挑战性。在这项工作中，我们训练一个用于参数生成的语言模型，该模型可以在细粒度的水平上进行控制，以生成给定主题，姿态和方面的句子级别的论点。我们将参数方面的检测定义为一种必要的方法，以允许这种细粒状控制和众包数据集，其中包含5,032个带有方面的参数。我们的评估表明，我们的一代模型能够生成高质量的特定于方面的论点。此外，这些论点可用于通过数据增强来提高立场检测模型的性能，并生成反对意见。我们发布所有数据集和代码以微调语言模型。
We rely on arguments in our daily lives to deliver our opinions and base them on evidence, making them more convincing in turn. However, finding and formulating arguments can be challenging. In this work, we train a language model for argument generation that can be controlled on a fine-grained level to generate sentence-level arguments for a given topic, stance, and aspect. We define argument aspect detection as a necessary method to allow this fine-granular control and crowdsource a dataset with 5,032 arguments annotated with aspects. Our evaluation shows that our generation model is able to generate high-quality, aspect-specific arguments. Moreover, these arguments can be used to improve the performance of stance detection models via data augmentation and to generate counter-arguments. We publish all datasets and code to fine-tune the language model.
