Affiliation:
1. University of Chinese Academy of Sciences, China
2. Gaoling School of Artificial Intelligence, Renmin University of China, and Beijing Key Laboratory of Big Data Management and Analysis Methods, China
3. Microsoft, USA
4. Microsoft Research Asia, China
Abstract
In this article, we study the problem of personalized news headline generation, which aims to produce not only concise and fact-consistent titles for news articles but also decorate these titles as personalized irresistible reading invitations by incorporating readers’ preferences. We propose an approach named
PNG
(
P
ersonalized
N
ews headline
G
enerator) by utilizing distant supervision in readers’ past click behaviors to resolve. First, user preference representations are learned through a knowledge-aware user encoder that comprehensively captures the genuine, sequential, and flash interests of users reflected in their historical clicked news. Then, a user-perturbed pointer-generator network is devised to accomplish the headline generation in which the learned user representations implicitly affect the word prediction. The proposed model is optimized by reinforcement learning solvers where indicators on factual, personalized, and linguistic aspects of the generated headline are regarded as rewards. Extensive experiments are conducted on the real-world dataset PENS,
1
which is a large-scale benchmark collected from Microsoft News. Both the quantitative and qualitative results validate the effectiveness of our approach.
Funder
National Natural Science Foundation of China
Project of Youth Innovation Promotion Association CAS, Beijing Nova Program
MSRA Young Visiting Researcher Program
Publisher
Association for Computing Machinery (ACM)
Reference65 articles.
1. Enrique Alfonseca, Daniele Pighin, and Guillermo Garrido. 2013. Heady: News headline abstraction through event pattern clustering. In Proceedings of ACL. 1243–1253.
2. Neural News Recommendation with Long- and Short-term User Representations
3. PENS: A Dataset and Generic Framework for Personalized News Headline Generation
4. Philip Bachman and Doina Precup. 2015. Data generation as sequential decision making. In Proceedings of NIPS. 3249–3257.
5. Headline generation based on statistical translation