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.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
