A Neural Approach to Irony Generation
This work addresses the challenge of irony generation for social media applications, which is an incremental advance as it builds on prior irony detection research.
The paper tackled the problem of generating ironic sentences by framing it as a style transfer task, using a large-scale Twitter dataset and a reinforcement learning approach with combined rewards, achieving effectiveness in irony accuracy, sentiment preservation, and content preservation.
Ironies can not only express stronger emotions but also show a sense of humor. With the development of social media, ironies are widely used in public. Although many prior research studies have been conducted in irony detection, few studies focus on irony generation. The main challenges for irony generation are the lack of large-scale irony dataset and difficulties in modeling the ironic pattern. In this work, we first systematically define irony generation based on style transfer task. To address the lack of data, we make use of twitter and build a large-scale dataset. We also design a combination of rewards for reinforcement learning to control the generation of ironic sentences. Experimental results demonstrate the effectiveness of our model in terms of irony accuracy, sentiment preservation, and content preservation.