A Neural Approach to Irony Generation
Mengdi Zhu, Zhiwei Yu, Xiaojun Wan

TL;DR
This paper introduces a neural method for generating ironic sentences by leveraging a large-scale Twitter dataset and reinforcement learning to control irony, sentiment, and content preservation.
Contribution
It is the first to systematically define irony generation as a style transfer task and to build a large irony dataset for this purpose.
Findings
Effective irony generation demonstrated by high irony accuracy
Successful sentiment and content preservation in generated sentences
Reinforcement learning rewards improve irony control
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSentiment Analysis and Opinion Mining · Topic Modeling · Multimodal Machine Learning Applications
