Learning to generate news headlines with media's stance
Journal
Proceedings - 2020 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2020
Pages
554-559
Date Issued
2020
Author(s)
Abstract
News headline generation can be viewed as a subtask of summarization. When it comes to news headlines or their source articles, positions and stances are usually the main concern for both the publisher and the readers. However, this aspect of headlines is rarely explored along with the developed headline generators. In this paper, we initiate a headline generation task considering the stance for a specific party. We extend the base model with different ways to include stances and investigate their pros and cons. We also propose approaches to evaluate the performance of handling stances. Finally, we come up with an ensemble model to cope with generation quality and stance consideration at the same time, whose results are comparable to human-written headlines. © 2020 IEEE.
Other Subjects
Base models; Ensemble modeling; Headline generation; Subtask; Intelligent agents
Type
conference paper