One of the challenges in text generation is to control text generation as intended by the user. Previous studies proposed specifying the keywords that should be included in the generated text. However, this approach is insufficient to generate text that reflect the user's intent. For example, placing an important keyword at the beginning of the text would help attract the reader's attention; however, existing methods do not enable such flexible control. In this paper, we tackle a novel task of controlling not only keywords but also the position of each keyword in the text generation. To this end, we propose a task-independent method that uses special tokens to control the relative position of keywords. Experimental results on summarization and story generation tasks show that the proposed method can control keywords and their positions. The experimental results also demonstrate that controlling the keyword positions can generate summary texts that are closer to the user's intent than baseline.

The world of search and user intent is more than just digital marketing and analytics, it has now evolved into a science. Once you have a solution to a pain point and you solve one minuscule issue from a massive compilation of data, consider yourself a professional who loves solutions. In the year 2022, we'll want to continue to advance and adapt with digital marketing shifts and customer wants and needs. With these two ideas, the world of AI aka artificial intelligence, is born. What we as digital marketers need to figure out is what is the pain point?